Temporally Coherent Imitation Learning

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 25

Oct 1, 2026cs.RO

Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch

With the increasing use of robot-free demonstration interfaces that provide state trajectories without action labels, imitation from observation has become a promising approach for learning robot behaviors from human demonstrations. However, due to differences in embodiment and dynamics between humans and robots, demonstrated human motions may not be feasible for the robot, potentially degrading policy performance. In this study, we propose Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation (EF-GAIfO), which estimates the feasibility of state-only demonstrations from the robot's own experience rather than relying on explicit dynamics models or large prior exploration datasets. A key feature of EF-GAIfO is that the notion of feasibility evolves with policy learning: as the policy improves and the robot experiences a broader range of state transitions, the feasible region is progressively expanded, allowing additional demonstrations to be incorporated into learning. This enables feasibility-aware imitation that adapts to the current stage of policy learning, rather than relying on a pre-designed feasibility criterion. We validate the effectiveness of EF-GAIfO on a locomotion task in simulation and on a real quadruped robot performing a object-reaching-and-grasping task.

Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki +2

Division of Information Science, Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan · Department of Industrial Engineering of the University of Trento, Trento, Italy

Temporally Coherent Imitation Learning Embodiment Imitation Robotic Grasping

Sep 29, 2026cs.RO

Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control

While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller. In this paper, we propose an imitation learning policy that predicts wrenches as its sole action output for direct use by a pure force controller. Our studies suggest that force-domain imitation learning depends critically on data collection, with force-feedback teleoperation improving policy performance by capturing the operator's deliberate force regulation. Using Action Chunking with Transformers (ACT) as the base architecture, we train single-task models on bilateral wrench demonstrations and evaluate them on five contact-rich manipulation tasks. The wrench policy matches or outperforms position-based baselines across all tasks, with gains varying according to the degree of deliberate force regulation each task requires. Cross-condition ablations show that the bilateral data collection interface and the wrench action space each contribute independently to performance. To support further research, we will release over 1000 wrench-action demonstrations spanning these tasks on a companion website upon publication.

Johannes Hechtl, Yannik Blei, Simon Ball +5

Siemens Research and Predevelopment · Department of Computer Science and Artificial Intelligence, University of Technology Nuremberg, Germany

Robotic Manipulation Policies Contact Wrench Estimation Contact-Rich Manipulation Robot Policies Scalable Robot Learning Temporally Coherent Imitation Learning+3

Sep 27, 2026cs.RO

Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control

Simulation-trained manipulation policies can exploit privileged state information to learn effective contact-rich behaviours, but deployment requires acting from partial observations such as noisy camera images. A common solution is teacher-student distillation, in which a visuomotor policy is trained to reproduce the actions of the privileged expert. This requires the student to jointly infer the task-relevant state and relearn the expert's action mapping that is already available. An alternative is to reuse the state-based expert and learn only a perceptual interface that reconstructs its missing state inputs. However, minimising the state estimate error alone does not necessarily minimise the downstream control error induced by these estimates. To bridge this gap, we train a visual state estimator using both direct state supervision and an action-consistency loss backpropagated through the frozen, differentiable expert. A scheduled objective first establishes a physically meaningful state estimate and progressively emphasises errors that affect the expert's actions. Across five goal-conditioned manipulation tasks, retaining the expert consistently outperforms direct pixel-to-action imitation from the same expert demonstration corpus. We further demonstrate sim-to-real transfer on a physical Panda robot, achieving 76% success without retraining the underlying expert.

Denis Shcherba, Adrian Abel, Eckart Cobo-Briesewitz +3

Fraunhofer Heinrich-Hertz-Institut, Berlin, Germany · Technische Universität Berlin, Germany

Visuomotor Policy Temporally Coherent Imitation Learning Visuomotor Control Reuse

Sep 14, 2026cs.RO

Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining

Applying an imitation learning policy to a new manipulation task usually requires collecting new demonstrations and retraining the model, which makes sample efficiency a practical concern. Pretraining on large-scale robot datasets is effective in this respect, but such datasets are costly to collect and train on, while data augmentation techniques typically require a new round of data generation and retraining for each task. A complementary question is what useful prior can be provided to a policy at negligible cost before any task-specific data are collected. In this study, we construct a geometric visual pretraining dataset in which each scene contains only a plane, an object, and a hand, and trajectories are generated automatically. The scenes contain neither textures nor backgrounds; pretraining primarily exposes the policy to the geometric relationship between the hand and the object. Furthermore, representing the hand as a cube avoids tailoring the dataset to a specific robot morphology. We evaluate this geometric prior using ACT on three simulated robots across five manipulation tasks each, as well as on three real-world robot tasks. Across many of these robot--task combinations, fine-tuning from the geometric prior achieves higher success rates in the early stages of training than training from scratch while using only a small number of task demonstrations. These results suggest that even highly simplified geometric scenes can provide a useful initialization that transfers across robots and to real-world tasks when task data are limited.

Shogo Iwakata, Tomohiro Motoda, Ryosuke Yamada +8

Waseda University · Embodied AI Research Team, AIRC and National Institute of Advanced Industrial Science and Technology (AIST) · Computer Vision Research Team, AIRC and National Institute of Advanced Industrial Science and Technology (AIST) +3

Temporally Coherent Imitation Learning Imitation Learning Large-Scale Robot Demonstration Datasets Imitation

Aug 6, 2026cs.HC

Turing's First Imitation Game: Design Concepts and a Human-Approximates-Machine Reading

This paper examines Turing's 1948 report, "Intelligent Machinery", as an important conceptual source for the later imitation games. Its first contribution is to identify and integrate the design concepts underlying the 1948 chess-based imitation game: the possibility that intelligent machines may make mistakes, the exclusion of irrelevant physical features, the role of the human judge, and Turing's claim that intellectual activity consists mainly of search. The paper's second contribution is to argue that restricting the human contestant to a rather poor chess player increases the role of intellectual search and makes human behaviour more comparable to machine behaviour. This interpretation presents the 1948 game as a human-approximates-machine game and suggests that the imitation game framework can be used not only to ask whether machines imitate humans, but also to examine when human intelligence becomes machine-like under specific task constraints.

Sharon Temtsin, Christoph Bartneck

University of Canterbury Christchurch, New Zealand

Counter Turing Test Imitation Temporally Coherent Imitation Learning

Aug 4, 2026cs.RO

Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion Retargeting

Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding references that are difficult for reinforcement learning (RL) policies to reproduce, particularly for contact-rich behaviors. We present a contact-implicit, direct simulation-based multiple shooting (DSMS) framework that transforms kinematically feasible references into dynamically feasible whole-body trajectories. By embedding a differentiable simulator within a nonlinear program, DSMS resolves contact, friction, impacts, self-collision, and joint limits internally while enforcing tracking, actuation, and task constraints without prescribing a contact schedule or introducing explicit contact constraints. Compared with existing retargeting methods, DSMS accelerates motion-imitation RL training and yields policies with high success rates and low tracking error. We further demonstrate zero-shot sim-to-real transfer on the Unitree G1 through command-conditioned contact-rich crawling and a highly dynamic 180-degree jump-turn.

Sergio A. Esteban, Jason H. K. Siu, Derrick Mach +4

Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, CA, USA. · School of Computing, DePaul University, Chicago, IL, USA.

Cross-Embodiment Retargeting Rigid-Body Dynamics Motion Imitation Temporally Coherent Imitation Learning Kinematics Motion+1

Jul 31, 2026cs.RO

RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning

Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making learned policies brittle to camera perturbations. To address this, we propose \textbf{Ray-conditioned Vision Transformer Encoder (RayViT)}, a lightweight architecture that injects camera geometry into pretrained ViT backbones. RayViT represents camera geometry as a Plücker ray map, patchifies it into ray features, and uses gated cross-attention to produce a ray-conditioned class token. These ray features are added as dense positional embeddings, while the ray class token replaces the original ViT class token to provide a geometry-aware summary representation. We combine this approach with an auxiliary cosine similarity loss to consistently improve the performance and robustness for geometry-aware tokens. Experiments on sim- and real-robot tasks demonstrate that RayViT improves robustness by approximately 13 percentage points under camera perturbations in multi-task RoboCasa benchmark and by 1.78 average completed stages in real-world multi-task success rate compared to baselines.

Qian Wang, Longrui Chen, Peiran Sun +8

Karlsruhe Institute of Technology, Germany · University of Leeds, United Kingdom

Visual Geometry Grounded Transformer Robotic Perception Photometric Supervision Local Camera Pose Vision Encoders Temporally Coherent Imitation Learning+2

Jul 18, 2026cs.LG

Scalable Causal Imitation Learning

Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's observations are mismatched and unobserved confounders are present in expert demonstrations. By identifying appropriate adjustment sets via the sequential

π

-backdoor criterion, causal imitation learning (CIL) provides a framework for approximating the expert's policy from confounded data. However, existing CIL methods, Causal Behavioral Cloning (Causal BC) and Causal Generative Adversarial Imitation Learning (Causal GAIL), are designed for short-horizon, low-dimensional settings. When applied to continuous control tasks with long horizons and high-dimensional state-action spaces, these methods exhibit poor performance: Causal BC suffers from compounding errors, Causal GAIL is unstable and sample-inefficient, and sequential

π

-backdoor adjustment becomes impractical. We introduce Causal Soft Q Imitation Learning (SQIL) and Causal Inverse soft-Q Learning (IQ-Learn), two off-policy causal imitation learning algorithms that combine the causal adjustment framework with state-of-the-art inverse reinforcement learning objectives. Both algorithms operate on causally-adjusted state representations produced by an efficient approximation of the sequential

π

-backdoor criterion, exploiting the causal structure of continuous control environments to reduce the full-horizon adjustment to a fixed-size sliding window. We evaluate all methods in a suite of confounded environments and find that Causal SQIL and Causal IQ-Learn substantially outperform prior CIL algorithms on long-horizon tasks, sometimes surpassing the expert, whereas all causally unaware imitation methods fail to learn meaningful behavior.

Eylam Tagor, Mingxuan Li, Elias Bareinboim

Department of Computer Science, Columbia University

Temporally Coherent Imitation Learning Strong Imitation Learning Imitation Learning Causal

Jul 11, 2026cs.RO

Source-Lifted Flow Matching for Intervenable Multimodal Imitation

Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose among valid continuations from the same state. We propose Source-Lifted Flow Matching (SL-FM), a source-intervenable flow-matching policy that exposes such a handle while keeping the velocity field shared and latent-free (without a separate discrete-handle input). The handle selects only the source endpoint of the conditional flow, not a mode-specific field, preserving the standard formulation while avoiding decomposition into separate mode-conditioned dynamics. The core mechanism is Orthogonal Source Lifting, designed to prevent path-crossing ambiguity. Instead of partitioning target actions by mode, SL-FM lifts handle-specific sources into auxiliary orthogonal coordinates and keeps targets in the original action subspace. This preserves the demonstrated action distribution while allowing one shared field to carry different branches without merging at crossings. To keep handles usable across states, we learn a state-dependent source mixture end to end and use a responsibility floor, giving each handle weak supervision and mitigating dead modes. Experiments on crossing-flow diagnostics and robot-control benchmarks show that SL-FM converts passive source randomness into an actionable intervention variable. It removes crossing-induced composite trajectories, changes future routes in 91.1% of matched-prefix interventions, and achieves strong free-deployment performance, with improvements in several benchmark settings. Overall, source geometry provides actionable multimodal control without conditioning the velocity field on the selected mode.

He Zhang, Ying Sun, Ziyang Chen +6

The Hong Kong University of Science and Technology (Guangzhou) · AI2 Robotics

Multimodal Action Distributions Conditional Flow Matching Temporally Coherent Imitation Learning Imitation Learning Subspace

Jul 10, 2026cs.RO

Implicit Behavior Coordination from Sub-Task Demonstrations by Exploiting Overlap-Induced Multimodality

Long-horizon robotic rearrangement is commonly formulated as a skill-sequencing problem, where distinct behaviors are explicitly represented and coordinated by a planner or high-level policy. We investigate whether such explicit behavior identities and sequencing interfaces are necessary at all. We introduce implicit behavior coordination from sub-task demonstrations, where separately collected behaviors are coordinated without behavior identity labels, complete-task demonstrations, or task-ordering supervision. Our key observation is that overlap between sub-task demonstrations induces multimodal action distributions that need not be resolved through explicit behavior partitioning. Instead, this overlap-induced multimodality can be exploited as a coordination resource. We instantiate this idea with a shared Flow Matching policy that preserves multiple action modes and critic-guided in-sample planning that propagates task value across demonstrations and selects task-relevant modes. Experiments in Habitat and on a real robot show that implicit behavior coordination remains effective under reduced cross-behavior overlap, larger behavior mixtures, longer horizons, and execution failures, supporting the idea that long-horizon coordination can emerge directly from sub-task demonstrations without explicitly recovering or sequencing behavior identities.

Ahmed Shokry, Usama Ahmed Siddiquie, Sicong Pan +1

Humanoid Robots Lab and Center for Robotics, University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany

Human-To-Robot Transfer Behavior Cloning Temporally Coherent Imitation Learning Robotic Manipulation Global Coordination Conceptual Reorganization+1

Jul 1, 2026cs.LG

Language-Critique Imitation Learning from Suboptimal Demonstrations

Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights. These scalar signals are inherently limited, as they cannot explicitly express intermediate reasoning about task progress, failure modes, or corrective actions. We propose a language-critique framework for imitation learning from suboptimal demonstrations that instead leverages natural language as a structured supervision signal, avoiding the collapse of expressive feedback into scalars. Our method first constructs language labels from demonstrations that explicitly describe current progress, identify suboptimal behaviors, and provide fine-grained corrective guidance. We then introduce a language-critique loss that directly trains policies using these structured signals without reducing them to scalars, and instantiate it for both behavior cloning and diffusion policies, yielding LC-BC and LC-DP. We further provide a theoretical result showing that the proposed objective upper-bounds the expert performance gap under standard assumptions. Empirically, we evaluate on diverse continuous control tasks spanning navigation, manipulation, and gameplay, where our methods consistently outperform strong imitation learning and offline reinforcement learning baselines. These results demonstrate that language can serve as a powerful and structured form of supervision for learning robust policies from suboptimal data.

Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang +3

Graduate Institute of Communication Engineering, National Taiwan University (NTU) · University of Utah · National Yang Ming Chiao Tung University +1

Temporally Coherent Imitation Learning Strong Imitation Learning Imitation Critique Feedback

Jun 24, 2026cs.RO

Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning

While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoning and spatial control. This creates a severe alignment bottleneck, limiting precise target disambiguation in data-constrained imitation learning. To overcome this, we propose SVP-IL, a decoupled architecture that explicitly extracts spatial visual grounding from the action generation loop. By leveraging vision-language foundation models, we parse instructions into zero-shot geometric masks, translating language into explicit Spatial Visual Prompts (SVP). These priors are injected into a continuous action generator via a lightweight direct feature-level fusion mechanism. This integration provides explicit and uncorrupted spatial gradient guidance while ensuring highly stable optimization under low-data regimes. Extensive experiments demonstrate that SVP-IL significantly outperforms state-of-the-art VLAs and pure visuomotor baselines. Trained on as few as 50 to 100 demonstrations, SVP-IL improves average success rates on highly ambiguous language-conditioned tasks from 24.0% to 39.5%, achieving 67.8% on standard benchmarks. Real-world robotic experiments further validate its robustness and data efficiency in unstructured physical environments.

Yanzhe Tang, Xinyu Shao, Yuxuan Hu +6

1Tsinghua University, Shenzhen, China. · 2Huawei Technologies Co., Ltd., Shenzhen, China. · 3National University of Singapore, Singapore.

Temporally Coherent Imitation Learning Spatial Grounding Geometric Guidance

Jun 18, 2026cs.RO

VFILC: Accurate Frequency Extrapolations in Imitation Learning via Sampling Frequency ILC

Conventional neural network (NN)-based imitation learning methods for variable-speed motion either restricted their scope to interpolated speeds, or generated unpredictable motions when extrapolating beyond trained velocity ranges. Variable-frequency imitation learning (VFIL) enabled extrapolations of speeds by linking the NN model's sampling frequency to the motion frequency, whereas its open-loop configuration caused frequency errors, especially in the extrapolated high-frequency settings. This study proposes variable-frequency imitation learning with iterative learning control (VFILC) based on a combination of VFIL and iterative learning control (ILC) with both feedforward and feedback parts, the former taking advantage of VFIL and the latter adjusting the frequency errors. The experimental results showed that the proposed method successfully and accurately extrapolated motion speeds and reduced frequency errors in all three tasks, and that the feedback especially reduced the frequency errors by a remarkable 81% in the wiping task and 50% in the shaking task, both compared to simple feedforward VFIL, when extrapolating at double the average speed in the training data. The proposed method also improved accuracy by 27% compared with VFIL even at an interpolated frequency for a contact-rich mixing task affected by complex friction traits.

Nozomu Masuya, Toshiaki Tsuji, Sho Sakaino

Grad. School of Science and Technology University of Tsukuba Tsukuba, Japan · Grad. School of Science and Engineering Saitama University Saitama, Japan · Systems and Information Engineering University of Tsukuba Tsukuba, Japan

Temporally Coherent Imitation Learning Imitation Learning Generative Control Policies Imitation Speeds Extrapolation

Jun 9, 2026cs.CV

LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching

Learning high-quality latent actions from large-scale unlabeled videos, coupled with limited real-world interaction data for training an action decoder, has emerged as a promising paradigm for scalable latent policy learning. However, existing approaches typically rely on behavior cloning, which tends to collapse inherently multimodal action distributions into unimodal ones, thereby degrading the pretrained latent action structure. While flow matching provides a potential alternative, directly applying it leads to a misalignment between latent actions and physical actions during action decoder training, due to the stochastic nature of the learned policy. To address these, we propose Latent Action Flow Policy (LAFP), which leverages flow matching for latent policy learning and introduces an inference-time interpolation mechanism to mitigate stochasticity-induced misalignment. Experimental results demonstrate that LAFP consistently outperforms prior methods on downstream imitation learning tasks, achieving up to 10-15% improvement in success rate while incurring less than 1x additional inference overhead.

Jiexi Lyu, Xizhou Bu, Qingqiu Huang +4

Latent Action Models Latent Actions Temporally Coherent Imitation Learning Behavior Cloning Stochastic

May 31, 2026cs.RO

Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry

Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this latency, they inevitably discard the intermediate trajectory evolution that provides crucial action correction. Directly recovering this mechanism by explicitly estimating a training-time drifting field is mathematically ill-posed due to extreme conditional demonstration sparsity. We introduce Implicit Drifting Policy (IDP), a one-step imitation learning framework that brings the training-time correction of Drifting into policy learning without explicit vector field estimation. IDP extracts a conditional expert geometry from the local variation of observation-similar expert actions, and compares it against a global reference geometry to isolate condition-specific constraints. This local geometric structure adaptively weights a scalar potential objective. Combined with an expert-proximal terminal evaluation, IDP directly enforces manifold constraints on the one-step generator during training. Extensive evaluations across 2D, 3D, and real-world manipulation tasks show IDP effectively maintains adherence to valid action manifolds, improving upon explicit drifting methods and achieving competitive performance with strong one-step baselines.

Zemin Yang, Yaoyu He, Yiming Zhong +5

ShanghaiTech University · Shanghai Jiao Tong University · The Chinese University of Hong Kong +1

Temporally Coherent Imitation Learning Imitation Learning Action Generation Vector Fields Experts

May 27, 2026cs.LG

Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning

Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observation spaces prevalent in robotics. This paper addresses the irreducible imitation gap that emerges when teacher and student are learned in isolation, and the teacher policy has the liberty to rely on privileged state information that the student cannot infer from its observations. Instead of improving poor student performance with RL finetuning after IL, which often requires a whole new training setup, we propose a novel algorithm which learns a shared embedding space that hides agent-specific observations and thus trains imitable teacher policies by construction. We train the shared embedding space with self-supervised contrastive learning in parallel to the teacher policy and prevent it from extracting private information by limiting its gradients from updating the encoder networks. We perform evaluations on several example domains and compare to state-of-the-art baselines showing that our algorithm enables higher student performance with substantially reduced imitation gap.

Meraj Mammadov, Pedro Zuidberg Dos Martires, Johannes Andreas Stork

Department of Computer Science Örebro University

Temporally Coherent Imitation Learning Imitation Learning Imitation Teacher Contrastive Learning

May 25, 2026cs.CV

MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control

Enabling physics-based humanoids to execute diverse behaviors from high-level textual commands remains a significant challenge. Existing methods typically follow either a two-stage paradigm that combines kinematic motion generation with physics-based tracking, or an end-to-end imitation-learning paradigm that directly generates actions from text. However, the former suffers from the inherent domain shift between kinematic generation and physics-based tracking, while the latter struggles with the substantial modality gap between textual commands and low-level actions, limiting effective semantic alignment. Notably, humanoid states encode rich motion dynamics that are more semantically aligned with textual descriptions than low-level actions, making them a natural basis for deriving behavioral intent. Building upon this insight, we propose MIND, a novel end-to-end diffusion framework for text-driven physics-based humanoid control that leverages behavioral intent as a semantic bridge between textual commands and low-level actions. At its core, MIND introduces a multi-scale intent diffusion mechanism, where a holistic intent predictor captures global behavioral dynamics to guide overall behavior synthesis, while an immediate intent predictor provides step-wise, fine-grained signals for local behavior refinement at each diffusion step. This hierarchical intent formulation imposes a structured inductive bias for humanoid control, improving semantic alignment and behavioral naturalness. Furthermore, MIND encodes humanoid states into a latent space to enable more effective semantic intent modeling. Extensive experiments demonstrate that MIND outperforms existing methods and synthesizes coherent, physically plausible, and semantically aligned humanoid behaviors from text commands. Project page: https://binlee26.github.io/MIND_page.

Bin Li, Ruichi Zhang, Han Liang +4

ShanghaiTech University, China · University of Pennsylvania, USA · Bytedance Seed, China +3

Full-Body Humanoid Control Human Motion Generation Multimodal Diffusion Models Temporally Coherent Imitation Learning Text-Driven

May 19, 2026cs.RO

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore how reinforcement learning (RL) should adapt policies after offline pretraining. Existing lightweight methods commonly apply residual corrections directly in action space, but this often leads to noisy and poorly structured exploration. In this work, we propose Z-Perturbation Reinforcement Learning (ZPRL), an approach that steers pretrained policies through a compact bottleneck latent rather than through policy weights or output actions. During offline training, we augment the policy with a plug-and-play variational information bottleneck (VIB) module to extract a task-relevant latent interface from observation embeddings. During online finetuning, the base policy is frozen and RL learns only a residual perturbation on this latent, whose decoded representation conditions the frozen action generator. We instantiate ZPRL on flow-matching policies and evaluate it on eight simulation tasks and four real-world tasks. Across diverse manipulation settings, ZPRL improves both sample efficiency and final performance over strong post-training baselines. In the real world, ZPRL improves the average success rate on four tasks by 33.7% over imitation base policies while producing smoother exploration behaviors than an action residual counterpart. These results suggest that a compact, task-aligned bottleneck latent provides an effective interface for online RL adaptation. More videos can be found at https://manutdmoon.github.io/ZPRL/.

Dongjie Yu, Kun Lei, Zhennan Jiang +2

School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR. · Shanghai Qizhi Institute, Shanghai, China. · Shanghai Jiao Tong University, Shanghai, China. +2

Robot Policies Temporally Coherent Imitation Learning Robotic Manipulation Robot Systems Action Generation

May 15, 2026cs.CV

Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce \textbf{VLA-AD}, a distillation framework that uses a Vision-Language Model as an offline semantic supervisor to transfer large VLA teachers into lightweight student policies. Instead of relying only on low-level action imitation, VLA-AD augments teacher-provided 7-DoF action targets with high-level semantic guidance, including task phase anchors and multi-frame operating-direction descriptions. These auxiliary signals are used only during training: at test time, the student policy runs independently, with neither the VLA teacher nor the VLM required. We evaluate VLA-AD on three LIBERO benchmark suites. Using OpenVLA-7B as the teacher, our method produces a 158M-parameter student, yielding a

44\times

reduction in model size while matching the teacher with only a

0.27\%

average relative gap. The resulting policy runs at 12.5 Hz on an RTX 4090, achieving a

3.28\times

inference speedup over OpenVLA-7B. We further show that the same semantic distillation pipeline generalizes to a different

π_{0.5}

-4B teacher, where the student outperforms the teacher on two suites and remains within

0.53\%

on \texttt{libero_goal}. Additional analysis indicates that phase-level supervision and multi-frame directional cues make the student less sensitive to noisy teacher actions, such as erroneous high-frequency gripper changes. Overall, VLA-AD demonstrates that offline semantic guidance from VLMs can substantially improve the efficiency, robustness, and deployability of VLA policy distillation.

Jin Shi, Brady Zhang, Yishun Lu

Department of Mechanical Engineering University College London London, United Kingdom · Department of Engineering Science University of Oxford Oxford, United Kingdom

Action Space Temporally Coherent Imitation Learning Geometric Guidance Guidance

May 15, 2026cs.RO

GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling high-dimensional RGB representations into control-relevant geometry without overfitting. While using frozen pre-trained Vision Foundation Models (VFMs) improves data efficiency, it also shifts most task adaptation onto a small spatial pooling module, which can latch onto task-irrelevant shortcuts and lose geometric grounding when finetuned with few data samples. More broadly, pre-trained visual representations used for policy learning have been observed to struggle under even minor scene perturbations, highlighting the need for robustness-oriented inductive biases. We propose Geometric Anchor Pre-training (GAP), a simple, action-free warm-up stage that regularizes the spatial adapter before downstream imitation learning. GAP pre-trains the pooling layer on a lightweight simulated proxy task where object masks are available at no cost, encouraging the adapter to produce keypoints that lie on the object, cover its spatial extent, and remain sharp and repeatable over time. This yields stable geometric anchors that provide a reliable coordinate interface for few-shot policy learning, while keeping the VFM frozen. We evaluate GAP on RoboMimic and ManiSkill under severe data scarcity (15-50 demonstrations) and domain shift. A simple adapter regularized with GAP consistently outperforms stronger attention-based poolers and end-to-end fine-tuning, achieving 62% success on RoboMimic Can with 15 demonstrations (+16% over AFA), 63% on the long-horizon high-precision Tool Hang task with 50 demonstrations, and 61% on ManiSkill StackCube with 30 demonstrations (+11% over full fine-tuning). The proxy stage is lightweight and fully decoupled from downstream tasks, making it practical to reuse across environments and manipulation skills.

Davide Buoso, Andrea Protopapa, Stefano Di Carlo +2

Department of Control and Computer Engineering, Polytechnic University of Turin, Italy

Visuomotor Policy Temporally Coherent Imitation Learning Frozen Vision-Language Models Long-Horizon Task Planning

May 9, 2026cs.LG

Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift

Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment settings the test environment's transitions differ from training, and classical offline IL offers no recourse: the learner must commit to an action at every state, even when its demonstrations are uninformative and could lead to arbitrary degradation of performance. This motivates the study of selective imitation, where the learner may choose to stop when it cannot act reliably. We introduce a model for selective imitation under arbitrary dynamics shift: given labeled expert demonstrations from a training environment and unlabeled state trajectories from the same expert in a test environment, the learner outputs a selective policy that is complete (rarely stops in training) and sound (incurs low regret before stopping in test). Our algorithm, SeqRejectron, constructs a stopping rule using a small set of validator policies whose size is independent of the horizon or policy class. For deterministic policies, this yields horizon-free

\tilde{O}(\log|Π|/ε^2)

sample complexity, assuming sparse costs. For stochastic policies, we obtain analogous horizon-free guarantees using a cumulative Hellinger stopping time. We extend the framework to misspecified experts and different expert policies across train and test and obtain results that gracefully degrade with the amount of misspecification.

Surbhi Goel, Jonathan Pei, James Wang

Strong Imitation Learning Temporally Coherent Imitation Learning Behavior Cloning

May 8, 2026cs.LG

Zero-shot Imitation Learning by Latent Topology Mapping

Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a fixed demonstration dataset contains useful behavior, but not complete examples for every task the agent must solve. Existing imitation learning methods can learn strong policies from demonstrations, but when solving long-horizon tasks, small errors accumulate over long primitive-action trajectories and make zero-shot adaptation to new tasks unreliable. We introduce Zero-shot Agents from Latent Topologies (ZALT), an imitation-learning method that solves unseen start-goal tasks beyond those demonstrated during training. ZALT identifies latent hub states where trajectories converge or diverge, learns policies and a dynamics model over hub-to-hub transitions, and plans over the hub topology to complete new tasks. This topology makes demonstrated behaviors explicitly composable while compressing long tasks into shorter sequences of abstract transitions -- combined, these enable ZALT to perform zero-shot adaptation. In a complex 3D maze environment, ZALT achieves 55% zero-shot success on unseen tasks, compared to 6% for the strongest baseline.

Maxwell J. Jacobson, Yexiang Xue

Purdue University, Department of Computer Science, West Lafayette, IN

Temporally Coherent Imitation Learning Imitation Learning Imitation Latent Action Models Topology

May 6, 2026cs.LG

Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations

We consider the stabilization of Vlasov--Poisson plasma dynamics, a central control problem in nuclear fusion. Our focus is the gap between what an ideal controller would use and what experiments can actually observe: while optimal policy may rely on the full phase-space state, practical feedback is typically limited to sparse macroscopic diagnostics. We therefore study imitation learning methods that distill a fully observed expert policy into controllers operating only on macroscopic measurements. We show the stability guarantees of the learned policy, where the error floor depends on the minimal behavior cloning loss achievable under the observation constraints. We further characterize this minimal loss in terms of a notion of entropy that quantifies the complexity of the initial distribution. Our results demonstrates the theoretical feasibility of learning stabilizing feedback policies for kinetic plasma dynamics from macroscopic observations, and exhibits the adaptivity of the learning approach to low-complexity structures. Through extensive numerical experiments, we validate our theory and show that the learned policies can stabilize the system using only macroscopic observations, within a significantly longer time horizon than non-adaptive baseline controllers.

Xiaofan Xia, Qin Li, Wenlong Mou

Department of Statistical Sciences, University of Toronto† · Department of Mathematics, University of Wisconsin–Madison⋄

Temporally Coherent Imitation Learning Phase Space Adaptive Control Imitation Optimal Policies Instability+1

May 5, 2026cs.AI

Real-Time Evaluation of Autonomous Systems under Adversarial Attacks

Most evaluations of autonomous driving policies under adversarial conditions are conducted in simulation, due to cost efficiency and the absence of physical risk. However, purely virtual testing fails to capture structural inconsistencies, supervision constraints, and state-representation effects that arise in real-world data and fundamentally shape policy robustness. This work presents an offline trajectory-learning and adversarial robustness evaluation framework grounded in real-world intersection driving data. Within a controlled data contract, we train and compare three trajectory-learning paradigms: Multi-Layer Perceptron (MLP)-based Behavior Cloning (BC), Transformer-based object-tokenized BC, and inverse reinforcement learning (IRL) formulated within a Generative Adversarial Imitation Learning (GAIL) framework. Models are evaluated using Average Displacement Error (ADE) and Final Displacement Error (FDE). Inference-time robustness is assessed by subjecting trained policies to gradient-based adversarial perturbations across multiple intersection scenarios, yielding a structured robustness evaluation matrix. Results show that state-structure design and architectural inductive biases critically influence adversarial stability, leading to markedly different robustness profiles despite comparable nominal prediction accuracy (ADE < 0.08). Inference-time Projected Gradient Descent (PGD) attacks induce final displacement errors of up to approximately 8 meters. The proposed framework establishes a scalable benchmark for studying offline trajectory learning and adversarial robustness in real-world autonomous driving settings.

Adithya Mohan, Xujun Xie, Venkatesh Thirugnana Sambandham +1

AI Motion Institute, Technische Hochschule Ingolstadt, Germany

Causality-Aware End-To-End Autonomous Driving Temporally Coherent Imitation Learning Robust Trajectory

Jan 30, 2026cs.RO

CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation

Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which remains challenging for existing generative policies. Diffusion-based approaches offer strong modeling capacity but incur high inference latency, while flow matching enables fast, near-single-step generation yet often suffers from unstable execution when operating directly in the raw action space. We propose Continuous Latent Action Flow Policy (CoLA-Flow Policy), a trajectory-level imitation learning framework that performs flow matching in a continuous latent action space. By encoding action sequences into temporally coherent latent trajectories and learning an explicit latent-space flow, CoLA-Flow Policy decouples global motion structure from low-level control noise, enabling smooth and reliable long-horizon execution. The framework further integrates geometry-aware point cloud conditioning and execution-time multimodal modulation, using visual cues as a representative modality to enhance real-world robustness. Experiments in simulation and on real robots show that CoLA-Flow Policy achieves near-single-step inference, improves trajectory smoothness by up to 93.7% and task success by up to 25 percentage points over raw action-space flow baselines, while remaining significantly faster than diffusion-based policies.

Wu Songwei, Jiang Zhiduo, Sun Wandong +4

Harbin Institute of Technology, Harbin 150001, China · Honor Device Co., Ltd., Shenzhen, China

Temporally Coherent Imitation Learning Flow Policies Multimodal Action Distributions Robotic Manipulation Latent Flow