Overview

Robot learning studies how robots can turn observations and experience into actions, from precise manipulation and locomotion to navigation and human-robot interaction. Common approaches include imitation learning from human or robot demonstrations, reinforcement learning through interaction, model-based control, and vision-language-action models that connect instructions and images to actions. Researchers also use reusable skills, structured physical representations, tactile sensing, and simulation or world models to improve transfer across tasks, objects, and robot bodies. A central challenge is making policies reliable beyond their training data: larger and more varied datasets can help, but physical feasibility, sim-to-real transfer, long-horizon recovery, and evaluation that predicts real-world success remain open concerns.

Latest papers

340 papers40 papers in the last four weeks, down 41% on the four weeks before. 0.3% of all new papers.

Nov 12, 2026

Alloy: A Multi-Material Physics Engine for Robot Learning

Robots handle much more than rigid objects: towels, cables, water, sand. The simulators used to train robots at scale are strongest on rigid bodies, and adding another material usually means a second engine and hand-written glue between the two. We present Alloy, an open-source physics engine for robot learning in which rigid robots, cloth, cables, liquids, granular material and soft bodies share one scene. Each object is described once; Alloy assigns it to a solver suited to its material, couples the solvers inside every control step, and runs the scene in many parallel worlds on one GPU, or on a CPU. Every world carries a health grade, to help tell a failure of the physics from a failure of the policy. Alloy is built on Newton, MuJoCo Warp and Warp, and it is written to be driven by coding agents: its documentation ships inside the package, every error names its fix, and the engine is exposed as tools over the Model Context Protocol. In a cold test, agents that had never seen Alloy installed a pre-release from the package index and trained policies for walking, cable handling and pouring on a single GPU. We also report how throughput grows with the number of worlds, depth-camera throughput, agreement with closed-form references, and a reliability test over a thousand worlds.
Nov 11, 2026

Autonomous Trail Racing with a Bicycle Robot

Navigating off-road trails on a mountain bike requires diverse locomotion skills, including aerial maneuvers, cornering, and slip recovery, paired with sophisticated perception for scene understanding. Translating these capabilities to autonomous, two-wheeled robots remains a formidable challenge. We show that autonomous, high-speed trail navigation can be achieved through a single idea: encoding the trail as a semantic layer of the terrain. In simulation, this layer embeds the navigation task into the training environment; during deployment, it is reconstructed onboard from camera and LiDAR data. First, we introduce a unified learning framework that treats local navigation and locomotion as a joint optimization problem, bypassing the twist or pose command interface of classical control hierarchies. With fixed reward weights, the same framework produces both trail racing and agile parkour, shaped only through terrain semantics and episode length. Second, our perception pipeline combines a frozen vision foundation model with a lightweight dual-head decoder that predicts per-pixel terrain semantics and confidence scores, which are fused with LiDAR range measurements into an egocentric semantic elevation map at 30 Hz onboard an NVIDIA AGX Orin. We validate our framework on the Ultra Mobility Vehicle (UMV), a bicycle robot that autonomously raced across all sections of a kilometer-long, unstructured mountain bike trail at speeds exceeding 5 m/s and averaging 3.26 m/s. In simulation, our policy fails up to an order of magnitude less often than hierarchical baselines while driving faster.
Nov 10, 2026

Game-Enhanced Embodied Learning with Event and Foresight Pretraining

Human gameplay supplies paired observations, actions, and visual consequences that can supplement robot-policy training. We study event-and-foresight pretraining for InternVLA-A1.5, combining recorded keyboard/mouse event prediction with history-conditioned visual supervision through a frozen video model. Coverage-preserving anchor selection constructs one-second targets, and an attention mask prevents teacher-forced future actions from entering foresight queries. The selected corpus contains 394 recordings across 20 games, with 223.36 hours of recorded timestamp span and 2,072,084 training anchors. After 12,400 game-pretraining updates, we compare the resulting initialization with the public base under the same suite-specific robot fine-tuning protocol. Across four LIBERO suites, aggregate success increases from 1,718/2,000 (85.90%) to 1,811/2,000 (90.55%), a gain of 4.65 percentage points. Suite gains are 9.2, 6.8, 0.2, and 2.4 points on Spatial, Object, Goal, and Long. The 40-task breakdown shows 24 improvements, 10 declines, and six ties. These results support the practical value of the complete game-pretraining stage in this evaluated setting, while revealing heterogeneous task outcomes. The comparison includes additional optimization and does not isolate the effects of game data, the two objectives, or training variability.
Nov 10, 2026

From Egocentric Human Video to Robot Manipulation in the Era of Embodied Intelligence

Egocentric human video (EHV) records close-range hand-object interaction (HOI) and the temporal structure of everyday activities, offering a potentially scalable source of experience for robot manipulation. Using this experience for robot control requires recovering useful supervision without recorded robot actions and accounting for differences in morphology, viewpoint, and action space. We define Ego2Robot learning as the process of learning or adapting robot manipulation policies from EHV, organized into four learning paradigms: explicit embodiment transfer, explicit action and task supervision, egocentric video representation pretraining, and latent action and dynamics modeling. The four paradigms differ in what they derive from human video: robot-format demonstrations, interpretable supervision, visual representations, or predictive models of actions and dynamics. For each paradigm, we trace what EHV information is extracted, how robot policies use it, and when the additional data is required. Besides, we review the benchmark datasets that cover EHV, robot demonstrations, and synthetic and simulated resources. This paper links EHV data's contribution to the task information preserved and the robot-specific grounding used during training or deployment. Finally, we identify challenges in physical feasibility, agent coordination, in-context adaptation, controlled evaluation, and predictive control.
Nov 9, 2026

Curie's Jarvis: Autonomous Robotic Chemistry Experiments from Printed Protocols

A person running a bench experiment works from a printed instruction sheet, tells identical containers apart by the labels written on them, and looks at the bench again before each step. Lab automation usually works the other way around: the procedure is written as a script, and containers stand at fixed positions or carry fiducial markers. We present Curie's Jarvis, a system that lets a robot arm carry out a chemistry experiment on a bench set up for people. It reads the steps from a photo of the printed sheet, finds containers on an ordinary bench with no fixed positions or markers, tells identical-looking containers apart by reading their labels in four camera views, locates its target again before every step, and sets how each step is carried out, including its speed, from what is being handled. On a Franka Panda arm, Curie's Jarvis completed 5 of 5 runs of one protocol from a children's chemistry kit and 4 of 5 runs of another, with no human intervention, and in 160 locates on printed and handwritten labels it identified every container correctly. This brings robots a step closer to doing bench chemistry the way people do.
Nov 9, 2026

RoboACE: Adversarial Co-Evolution for Robot Self-Improvement

Robot agents can improve reusable skills, planning procedures, and recovery strategies from execution feedback, yet a fixed practice source leaves the search for new weaknesses unchanged. Useful practice depends on the agent's current capabilities, so the procedure that chooses practice must also be revisable. We present RoboACE (Robot Adversarial Co-Evolution), a framework that jointly evolves curriculum and execution harnesses around frozen foundation models. The curriculum harness uses accumulated capability evidence to propose informative challenges, while the execution harness responds with reusable revisions that expand execution capabilities. Alternating updates hold one side fixed as the other changes, and admitted challenges form fixed snapshots for comparing execution revisions. Starting from a compact set of LIBERO practice conditions, the resulting frozen deployment outperforms the evaluated controllers and agent systems across four LIBERO-family panels. On LIBERO-PRO, it reaches 74.0% success, exceeding the initial deployment by 15.0 percentage points and direct execution by its VLA controller by 13.5 points. Case studies document changes to evidence-guided practice selection, drawer-skill grounding, and controller intervention.
Nov 6, 2026

BATCH: Behavior Alignment for Cross-Embodiment Learning from Humans

Human demonstrations provide a scalable source of diverse manipulation data, but leveraging them for robot learning remains challenging due to differences in embodiment, viewpoint, action spaces, and temporal structure. We introduce BATCH, a cross-embodiment learning framework that explicitly aligns human and robot behaviors. BATCH learns self-supervised temporal representations with a cycle-consistency objective to establish cross-embodiment correspondences without manual annotation. We further introduce two complementary training objectives that leverage these correspondences within an autoregressive videoaction diffusion model: behavior-aligned co-training and human-to-robot style transfer. On real-world manipulation tasks, BATCH improves generalization to unseen task configurations compared with training on unaligned data and prior cross-embodiment baselines, with additional gains from the style-transfer objective. Our results demonstrate that explicit behavior alignment enables more effective transfer from human demonstrations to robot policies.
Nov 6, 2026

On Agentic Manipulation Policies

Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that generalist AI models can control manipulators more reliably than specialist policies such as vision-language-action models (VLAs) and world-action models (WAMs). We systematically analyze agentic manipulation policies (AMPs), in which a generalist AI model commands the manipulator directly, adapting its actions as the task unfolds. We present AMP1, a reference harness that runs unchanged across single-arm, bimanual, and mobile manipulation. AMP1 achieves state-of-the-art results on the RoboLab-120 and CaP-Gym benchmarks, with no demonstrations or task-specific training. On RoboLab-120, AMP1 reaches an 85.6% success rate zero-shot, compared to 49.2% and 42.9% for leading VLA and WAM policies. The agent succeeds zero-shot in 104 of 108 real-world trials spanning twelve tasks and three robot instances, reducing failure rates by 20x and 15x relative to strong VLA and WAM baselines. The basic harness supplies no grasping, pushing, or placing skills; the agent develops its own strategies, such as searching for hidden objects, using objects as tools, and calibrating its cameras. With the addition of a persistent memory store, the agent can also learn from experience: an augmented harness with a memory representation that is carried across episodes lowers the failure rate on RoboDojo bimanual manipulation tasks by 4.6x relative to zero-shot deployment. Our analysis suggests that AMPs are substantially more general and robust than specialist manipulation policies, providing a promising foundation for robot manipulation.
Nov 6, 2026

Augmentron: Scalable Multi-View Visual Augmentation for Robot Learning

Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that are unrelated to the task. Existing generative augmentation methods can introduce visual diversity, but processing every frame and camera view independently is computationally expensive and may produce inconsistent observations across cameras and timestamps. We introduce Augmentron, a geometry-aware pipeline that generates reusable scene representations and renders them through recorded camera poses. This produces temporally and multi-view consistent environ- ment and workspace variations while preserving the robot, task objects, actions, and annotations. Across three physical manipulation tasks, replacing half of the real world training dataset with Augmentron data improves model success across three tasks for both in out-of-distribution distractor objects, and out-of-distribution workspace variation evaluations. In a separate comparison against alternate augmentation techniques, Augmentron achieves the highest pooled success in all three conditions. The results show that introducing augmented data to a data training recipe can help policies generalize to dynamic real-world settings.
Nov 3, 2026

All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy

Visual Foundation Models (VFMs) provide semantic cues such as depth and segmentation useful for robotic manipulation, but directly deploying them in closed-loop control is impractical due to high computational cost, temporal inconsistency, and distribution shift between static internet images and egocentric robot observations. We propose All-For-One (AFO), a two-stage distillation framework that leverages VFMs strictly as privileged information during training, using downstream robotic data. Following the privileged learning paradigm, AFO decouples semantic representation learning from inference-time policy execution. In the All stage, a teacher policy fuses RGB observations with outputs from multiple VFMs to learn a semantically enriched representation. In the For-One stage, this knowledge is distilled in-distribution into a lightweight RGB-only student policy. Evaluated on two Adroit tasks and five MetaWorld tasks in simulation, as well as three real-world manipulation tasks, AFO outperforms prior foundation-model-based approaches while using over 30x fewer parameters than VFM-based encoders and 50x lower latency than its own teacher in simulation benchmarks, providing an efficient pathway for transferring foundation-model knowledge to robotic control.
Nov 2, 2026

Neuro Inspired Robotics: What Robot Learning Can Borrow from the Sensorimotor Brain

Robot policies still fail at everyday manipulation: an unfamiliar task, an object never held before, a scene that changes mid-motion, a skill that should improve with use. They fail despite pretraining on over a million trajectories, pooled from dozens of robots at great expense, while a child acquires all of these abilities within a few years of learning from a single body. This survey argues that the gap is one of design, and proposes designs for the next generation of robot models, drawn from how the nervous system solves the same problems. From the body we take compliance: the policy commands stiffness alongside position, so the controller yields where the task allows and presses where it must, which greatly lowers the demand for precise position output. From the visual system, where a fast pathway for action runs in parallel with the slow pathway for recognition, we take a dedicated fast vision system for motor behavior: it precomputes the quantities the policy needs and drives a reactive policy at camera rate. From the cerebellum we take a predictor beside the policy that forecasts the consequence of each command and recalibrates from its own error. From motor cortex we take a single model that composes action units from primitives, verifies each at a sensory boundary, practices the weakest unit with a hypothesis in mind, and reasons each attempt closer to the goal. Proven primitives are then consolidated from code into weights, so they run fluently and respond quickly the next time. Together these describe a robot that acts on its own initiative, the basis of deployment and recursive self-improvement, and we offer each proposal as a hypothesis to be tested.
Nov 1, 2026

Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining

In modern robot learning, generative robot policies are first pretrained through supervised learning from demonstrations, then refined through reinforcement learning, supervised finetuning, or other forms of posttraining. Yet conventional pretraining metrics, such as validation loss and average task success, provide an incomplete account of which policies support both effective direct deployment and subsequent posttraining. In this work, we study closed-loop pass@k, which evaluates the probability that k rollouts from the same initial condition attain at least one success. Thus, pass@1 measures mean task success; large-k pass@k measures whether success remains reachable under repeated sampling. Across a wide range of posttraining recipes, we show that large-k pass@k reveals posttraining differences not captured by pass@1. In particular, checkpoints with similar pass@1 but different large-k pass@k have different posttraining performance. Moreover, we show pass@k peaks at different checkpoints during supervised pretraining, revealing a coverage-reliability tradeoff over the course of training. Based on these observations, we propose two practical interventions: (1) a purely offline checkpoint-selection criterion that balances coverage and reliability without closed-loop evaluation, and (2) a generative data augmentation procedure that expands supervision beyond the finite demonstration set, preserving large-k pass@k while maintaining or improving pass@1 and raising the observed coverage-reliability Pareto frontier. Together, our results motivate evaluation, checkpoint selection, and training procedures that explicitly account for posttraining. Blog post, visualizations, and code are available at https://zhanyisun.github.io/robot-policy-learning-dynamics/.
Oct 30, 2026

Teach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots

Collaborative robots (cobots) are designed to be safer and more interactive than traditional industrial robots, share the same workspace as humans, and assist them in a range of shop-floor tasks such as palletization, joint assembly, and part inspection. Many of these tasks involve repetitive workflows that may evolve with changes in production environments and task specifications. These requirements motivate the need for intuitive interfaces that allow workers to modify workflows on the shop floor and generalise these routines for future use. This work introduces the Teach-Abstract-Apply (TAA) framework, which enables human operators to (a) teach new workflows to cobots in natural language, (b) abstract the taught workflows into skills for later use, and (c) apply these skills in different settings. As a case study, we apply the TAA framework to a collaborative structure-building task and evaluate it with both open-weight (Qwen3-Coder) and closed (GPT5.2-Codex) models in self-play and cross-model configurations. Our results show that skill abstraction improves task success rates and reduces interaction cost. Beyond automated evaluation, a preliminary human-in-the-loop study suggests that the pipeline also works with human instructions.
Oct 30, 2026

Learning from Physical Experience:Context-Space Adaptation for Robotic Manipulation

Recent multimodal foundation models exhibit strong perception, reasoning, and in-context learning capabilities, but translating these capabilities into physical action remains challenging. Through real-world experiments across diverse manipulation tasks, we find that ChatGPT-6-Astra, a state-of-the-art general-purpose reasoner, can serve as a physically actionable, context-responsive manipulation policy, demonstrating effective fine manipulation and spatial reasoning. Building on these findings, we introduce LEXP, a harness for learning from physical experience through context-space adaptation. LEXP combines task-level planning with an experience module that interprets execution evidence, extracts and retains lessons with applicability conditions, and reuses relevant lessons to generate contextual feedback for subsequent actions. Model weights and the action interface remain fixed throughout. Across 12 real-world manipulation tasks, LEXP achieves 23/3623/36 successful trials (63.9%), compared with 19/3619/36 (52.8%) with memory alone and 2/362/36 (5.6%) for vanilla Astra. On three tasks, bread transfer, sort trash and toiletries, and retrieve drawer, removing planning reduces success from 7/97/9 to 4/94/9, while removing retained experience reduces it to 3/93/9. Execution traces illustrate feedback-guided corrections and cross-episode reuse of an inspection strategy. Execution analyses illustrate how task structure and experience-derived feedback guide task progression, action correction, and experience reuse. These results support context-space adaptation as a practical mechanism for turning physical interaction into reusable guidance for robotic manipulation.
Oct 29, 2026

Is It the Curriculum or Just the Easy Start? Benchmarking Unsupervised Environment Design on Quadrupeds

Unsupervised environment design (UED) methods such as PLR, ACCEL, SFL and PAIRED are compared mostly on 2D mazes, grid worlds and BipedalWalker, while terrain curricula for legged robots are hand-designed and evaluated against a few baselines. We present a benchmark that runs fourteen UED, domain-randomisation and robotics curricula under one protocol on five 3D quadrupeds in MuJoCo MJX: the closed-chain W01-TEK and the open-chain Unitree Go1 and Go2, Google Barkour vB and Boston Dynamics Spot. Levels are vectors of eight interpretable terrain parameters, and all curricula drive the same PPO student at matched environment-step budgets. The evaluation reports success on random and held-out structured terrains, interquartile means with stratified bootstrap intervals, capability envelopes and a level-by-level domination comparison. We compare methods within each robot and report, per level set, the top group of methods not significantly below the best. No method is in the top group on every robot and level set. Methods with easy or low-difficulty training levels, curated or not, fill the top groups on in-distribution random levels of Go1 and Barkour, and of W01-TEK apart from PAIRED+BiBC. The success-driven terrain curriculum from legged-robot practice is in a top group most often, domain randomisation on uniform levels in none, and PAIRED in none outside Spot, where the fourteen methods lie within 3.8 points on random levels of difficulty 0.25. On three robots the leader on in-distribution random levels is not the leader on held-out terrain. We collect the results into a per-robot guide to choosing a curriculum.
Oct 29, 2026

PRIME W0: Physical Priors from World Models for Embodied Manipulation

Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context and the hierarchical structure of VLM representations. We present PRIME W0, a hierarchical conditional flow-matching framework that closes this gap through three synergistic designs: (1)per-layer KV injection from a pretrained VLM into an Adaptive MoE action expert; (2)dynamics-aware conditioning via asynchronous world-model subgoal-image prediction and a DINOv2 historical-frame semantic bridge; and (3)Action Dynamic Manifold (ADM) flow matching with covariance-structured noise that respects robot kinematic coupling. PRIME W0 is trained in four stages---VLM pre-training, DAT/NTP visuomotor pre-training, DiT flow-matching decoder assembly with WM injection, and end-to-end SFT---and achieves state-of-the-art results on LIBERO and real-robot benchmarks, with systematic ablations validating each architectural component.
Oct 26, 2026

Environment Edits as a Corrective Signal for Reward Learning

Robot corrections allow people to adjust a robot's behavior, but a single correction changes many features. Also, preferences about object attributes and relationships between objects cannot be expressed by moving the robot. We propose environment edits as a complementary form of feedback. The robot's motion is held constant as the human edits the scene, so the only explanation for the edit is the moved object. We introduce Feature Learning from Environmental and Robot-Relational Edit Traces (FERRET), which learns preferences from both robot and environment corrections. We show that environment edits are able to disambiguate features and learn preferences that robot corrections alone cannot.
Oct 26, 2026

From Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes

This work explores a multimodal approach to the alignment of the behavior of open-ended learning autonomous robots with human purposes through the use of large language models as cultural enablers. While autonomous robots can generate their own skills and goals through interaction with the environment, they often lack mechanisms to ensure that these remain relevant and aligned to those of human users. The proposed approach makes use of the general and cultural knowledge contained in LLMs and VLMs to establish a multimodal interactive alignment process in which human purposes, expressed in natural language, are transformed into motivational components of a robot architecture in the form of robot missions and drives that guide the behavior of the robot. The system is structured into three layers for semantic alignment, mission generation, and drive modeling. This design enables a bidirectional interaction loop: human inputs define high-level purposes, robots expand them into executable missions making use of multimodal information relayed by LLMs and VLMs, and feedback maintains alignment with human intent. Experiments in simulation and with a physical robot demonstrate that the process produces valid missions and behaviors, supporting effective human-agent alignment in interactive scenarios with autonomous robots.
Oct 26, 2026

Enhancing Deep Reinforcement Learning for Robotic Motion Planning via Task Decomposition

Obstacle-aware robotic manipulation can require substantial interaction data when deep reinforcement learning policies are trained from scratch. We study a task decomposition framework combining first-layer critic transfer with staged reward redesign (RR) on a Truncated Quantile Critics (TQC) backbone. Transfer reuses an input representation across tasks, while RR supplies intermediate feedback for Pick-and-Place. Experiments cover Push, Pick-and-Place, and Slide in obstacle-free and single-obstacle PyBullet environments, with three random seeds per setting. On obstacle-aware Push, transfer achieves 0.83±0.050.83\pm0.05 success against 0.77±0.060.77\pm0.06 for TQC. On obstacle-aware Slide, it achieves 0.95±0.020.95\pm0.02 against 0.84±0.060.84\pm0.06 for SAC, the strongest baseline in that setting. These are gains of 66 and 1111 percentage points, respectively. RR reduces the target-training steps needed for obstacle-free Pick-and-Place from roughly 0.750.75M to 0.200.20M. Transfer benefits depend on the route: obstacle-aware Pick-and-Place shows a lower mean than training from scratch. A selected simulated trajectory is executed open-loop on a Franka Emika FR3 as a feasibility demonstration. The study characterizes when a lightweight combination of established transfer and reward-design components helps learning.
Oct 25, 2026

What Does World Modeling Actually Improve in Robot Action Learning?

World Action Models (WAMs) combine future-video prediction with robot action learning, yet improvements in task success alone do not reveal how predictive supervision manifests in execution behavior or whether its benefits persist under task and environmental shifts. We conduct controlled future-video prediction loss ablations within FastWAM and OpenWAM, keeping model architecture, initialization, robot training data, and training steps fixed within each model family. Under clean conditions on seen tasks, predictive supervision increases success rates by 24.38 and 72.91 percentage points, respectively. Trajectory clustering further reveals higher success rates within several coarse trajectory clusters, including cases where cluster frequencies change little, indicating that the gains are not solely reflected in changes in the prevalence of trajectory patterns. However, these benefits do not consistently persist under distribution shifts: improvements on unseen tasks vary across models and tasks, while both models exhibit low success rates under the evaluated environmental randomizations, without a consistent advantage from predictive supervision. We further introduce future-video prediction as an auxiliary training objective for π0.5π_{0.5}, where a lightweight Transformer predictor used only during training increases success from 82.94% to 89.19%. These findings support future-video prediction as effective auxiliary supervision for action learning, while distinguishing improved execution on familiar tasks from reliable transfer and showing that such gains need not rely on a large pretrained video diffusion transformer (DiT) in the evaluated setting.
Oct 25, 2026

Learning Interaction-Aware Path Corrections from Unlabeled Trajectories: A LiDAR-Based Sim-to-Real GNN Framework for Construction Robots

Construction robots operating near workers require navigation that can anticipate human motion while remaining robust to dynamic and unstructured site conditions. However, existing social navigation methods depend on hand-crafted interaction rules, labeled demonstrations, or robot-specific control policies, limiting their scalability and transferability in construction environments. We propose a real-time, LiDAR-only framework that learns interaction-aware path corrections from unlabeled demonstrations. Constant-velocity extrapolation generates residual learning targets, while a GNN models relationships among the robot, pedestrians, and goal context. During deployment, an extended Kalman filter tracks LiDAR detections to construct dynamic graphs, and the GNN offsets planner-generated waypoints through a planner-agnostic interface. Within the bricklaying trial, the GNN reduced path irregularity by 39.2% and increased minimum TTC. Across Dynablox sequences, it increased minimum TTC by 38.3% while producing shorter, smoother paths than the baselines. Ablation studies supported a 1.0-s prediction interval and confirmed the benefits of target context, reflection augmentation, and feature normalization.
Oct 23, 2026

DynaSlots: Slot-Centric 3D Dynamics Pretraining for Robot Manipulation

Robot manipulation involves localized changes: picking up a cup moves the cup while leaving the surrounding scene largely unchanged. Yet existing 3D visual pretraining methods, including recent dynamics-aware variants, model state transitions at the scene level, compressing the motion of everything in a scene into a single global latent action. This conflates semantically distinct transitions in scenes with multiple moving parts, obscures dependencies between changing regions, and leaves the learned representation vulnerable to task-irrelevant scene content. We introduce DynaSlots, an action-free, label-free pretraining framework that decomposes each point cloud frame into a small set of temporally consistent slots and models dynamics at this per-slot level rather than the scene level. A temporal slot propagation module promotes consistent slot assignments across frames; an inverse dynamics model then extracts one latent action per slot from feature differences, and a diffusion-based forward dynamics model, paired with a self-supervised interaction head, predicts each slot's future state while learning pairwise proximity-and-motion relations. Experiments on Meta-World, Adroit, and a RealMan RM65-B robot demonstrate that DynaSlots outperforms prior scene-level baselines. It achieves superior success rates in simulation and exhibits strong robustness to scene clutter and unseen objects in real-world manipulation. Code is available at https://zhucezhanghao12345-source.github.io/DynaSlots-Anonymous/.
Oct 21, 2026

Robot Generalization Beyond Volume: The Diversity Path via Zero-Shot Capabilities

General-purpose robots must handle tasks, objects and environments they were never trained on, yet zero-shot generalization remains one of the least solved problems in physical AI. In digital AI, zero-shot capability grew with the volume and, above all, the diversity of training data, much of it sourced from the crowd. Robotics instead relies on paid collection by a few well-funded teams, which yields volume without diversity. We formulate zero-shot generalization in physical AI as coverage of the deployment distribution, and show that more samples from the same collectors shrink the unseen region only slowly, while each new contributor can extend it. Building on this and on zero-shot learning, we propose a shared latent space for robot actions that combines multi-modal alignment, generative augmentation, and noisy-label learning. As a scalable source of diverse data, we propose a community of developers building applications on one standard, approachable robot, Origami. We close with a testable hypothesis and an evaluation protocol relating real-robot zero-shot success to the diversity of contributed data.
Oct 21, 2026

Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies

Vision-language-action (VLA) policies need to recognize gaps in their training knowledge to request useful demonstrations or assistance in new situations, especially when failures are costly. Disagreement within an ensemble of independently trained policies can guide these decisions, but requires training and running multiple policies. We propose post-hoc kernel-variance heads that estimate epistemic uncertainty from the embeddings of a single policy. Each head computes the conditional variance of a Gaussian process conditioned on embeddings from the training demonstrations. Fitting requires no regression targets or gradient updates and leaves the policy unchanged. In experiments with SmolVLA on LIBERO-10, the kernel variance heads perform competitively with two-policy ensemble scores in task-level correlation with task success, in demonstration acquisition during active learning, and in referral to a stronger supervisor policy as a proxy for human assistance. For SmolVLA, the head on the vision-language backbone reduces uncertainty-scoring time by up to approximately a factor of 50 compared with ensemble scores, while also substantially reducing setup costs. We also show that the established evaluation protocol on LIBERO-10 primarily rewards recognition of coverage differences between tasks, while execution variability weakens assessment of within-task rankings. Thus, controlled perturbations provide a complementary evaluation: modality-specific heads identify unfamiliar camera, instruction, or state inputs, while fused heads can detect unfamiliar combinations of individually familiar inputs. With a supervisor proxy trained on the evaluated perturbation families, the decoder head improves within-task referral over ensemble disagreement. These findings show that useful uncertainty estimates for adaptive robot learning can be obtained from a single policy.
Oct 21, 2026

Toward Recursive Self-Improvement in Physical AI

Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which it improves. Recent digital agents test this idea by rewriting their own code and checking each version with executable tests. Bringing these mechanisms into the physical world requires learning from partial observations through costly trials, while accounting for changing operating conditions and potentially irreversible consequences. We position RSI within robot learning and trace pathways from improving robot capabilities to improving the processes that generate them. We examine how physical experience can strengthen these improvement mechanisms and when the resulting gains can support further self-improvement of the mechanisms themselves. Gains carry forward only when feedback addresses remaining learning needs, the receiving component can use the change, its value survives changes in tasks or hardware, and continued practice remains safe and affordable. Existing studies, concentrated in manipulation, support behavioral improvement, benefits to later learning, and procedure improvement. Some systems also change the improver's knowledge or tools, but the physical studies reviewed here have yet to isolate gains attributable to recursion. We synthesize these findings into evaluation principles and research directions for machines that, trial by trial, safely improve the way they improve.
Oct 21, 2026

From Association to Decision Value: Testing Paired Instruction Dependence for VLA Corpus Selection

Choosing among robot demonstration corpora is a ranking problem: an upstream diagnostic must preserve which candidates produce better downstream policies, not merely correlate with average performance. We study paired instruction dependence, the rate at which a demonstrator changes its first decision when only the goal changes. Across 136 independently seeded quadruped-navigation corpora, predictions developed on 56 corpora are evaluated prospectively on 80 held-out corpora. The audit is reliable and associated with downstream paired correctness, and lowers mean absolute prediction error when added to a correctness-aware baseline, but the primary proper-log-score increment is +0.059 nats (95% corpus-bootstrap CI [-0.027, 0.133]) and the prespecified top-20% comparison does not establish an incremental selection gain. An exploratory response decomposition suggests a structural source of this predictive-ranking mismatch: under the tested predictor specification, separating both-correct and both-wrong responses yields larger held-out gains than their unsigned switch statistic. Seed-to-seed agreement indicates that the held-out endpoint retains recoverable rank signal. These results show that counterfactual response structure can be reliable and predictive while providing limited incremental decision value in this setting when compressed into an unsigned statistic, motivating diagnostics that preserve outcome-relevant structure and are validated against the decisions they are intended to support.
Oct 21, 2026

Distance Field Driven Reinforcement Learning for Reactive and Robust Collision Avoidance

Robust and reactive collision avoidance remains a central challenge for deploying Reinforcement Learning (RL) policies on real robotic manipulators, particularly when transferring behaviours learned in simulation to the physical world. This paper presents an RL framework that integrates the Euclidean Distance Field (EDF) directly into the observation space, providing the agent with continuous geometric cues that support stable and responsive avoidance behaviours. By leveraging the rich spatial information encoded in the EDF, the method enables a streamlined reward formulation that achieves effective obstacle avoidance both with and without Artificial Potential Field guidance. The proposed approach is validated on a 7-DoF redundant manipulator, demonstrating zero-shot transfer from simulation to real hardware. Despite being trained exclusively with randomised static objects, the deployed policy generalizes to previously unseen real environments and exhibits robust online avoidance of dynamic obstacles. These results highlight the potential of EDF-based representations to mitigate the sim-to-real gap and support reliable and real-time collision-aware behaviour in complex and changing environments.
Oct 21, 2026

Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation

Large pretrained robot foundation models provide strong priors for manipulation, yet adapting them to target tasks with offline teleoperated demonstrations often fails to cover the contact-rich, recovery, and precision-critical states encountered during deployment. Existing methods mitigate this issue by augmenting offline demonstrations with human-in-the-loop data or online reinforcement learning. Despite this, offline post-training adapts slowly because it cannot immediately absorb deployment experience, while online RL typically relies on value functions or auxiliary actor-critic models, increasing both training complexity and instability. We present TIDE (Training In DEployment), a human-in-the-loop online post-training system. TIDE introduces a provenance-conditioned supervised learning framework that updates the policy online from human interventions and policy-generated rollouts collected during deployment, without a learned critic, reward model, or action scorer. Across four real-world bimanual manipulation tasks, TIDE improves milestone-normalized task progress and binary full-task completion over the warm-start policy and matched additional offline demonstrations, and performs comparably to the fixed-policy collection baseline while making updated checkpoints available during deployment. Each task-specific online post-training session, from the start of deployment rollouts until the final checkpoint is available, completes in less than one hour while learning and checkpoint handling run asynchronously.
Oct 20, 2026

GGraph: A GPU-Accelerated Library for Graph-Based Robot Deployment and Learning

Autonomous mobile robots require spatial representations that capture geometry and semantics while staying sparse enough for planning in large, unknown environments. Graphs provide a natural representation for this purpose and underpin both classical planning methods and a growing class of reinforcement-learning (RL) policies. However, RL training needs hundreds to thousands of parallel environments, each constructing and updating its own graph. Existing graph libraries are typically designed for either single-robot deployment or fixed graphs, and CPU-based graph construction limits scalable training to only a few dozen environments. We introduce GGraph, an open-source GPU-accelerated graph library for both robot deployment and large-scale learning. GGraph supports real robots through ROS 2 interfaces and vectorized GPU-based policy training, with built-in support for tasks including 3-D navigation, exploration, and loop-closure integration. For single-robot operation, GGraph updates graphs in milliseconds. At scale, it enables graph-based exploration policies to train across hundreds of parallel robots, reducing wall-clock training time by one order of magnitude. Across simulation and real-world experiments, these results establish GGraph as a unified graph infrastructure for both large-scale robot learning and deployment.
Oct 20, 2026

inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action

Long-horizon robotic operation requires memory that scales with essential information rather than execution time. We present a parameter-space memory framework where each episode is stored as a separable object. A neural implicit representation is fitted to episode video from a shared, meta-learned initialization; the resulting weight delta constitutes the memory. Crucially, this delta remains a fixed size regardless of whether the episode spans a hundred or a hundred thousand frames. A learned projector maps the weight delta into token embeddings, conditioning a language model for question answering and a decoder for joint command regression, without frame retrieval at query time. On RoboMME, the language model exceeds chance across all question types, and the decoder achieves a mean R2R^2 of 0.51. Replacing the delta with matched noise drops performance by 11.4 points, while random-origin weights are non-decodable, proving the meta-learned initialization is essential for embedding episode content. By representing individual experiences as fixed-size weight deltas in a common parameter space, this approach decouples memory cost from time horizon and provides a basis for scalable streaming memory.