Robot Policy Learning

Follow this topic Ask about this topic

Robot policy learning studies how robots can turn camera, depth, tactile, and proprioceptive inputs into actions for tasks such as manipulation, locomotion, and navigation. Common approaches include behavior cloning from demonstrations, reinforcement learning in simulation or on hardware, and diffusion, flow-matching, or vision-language-action policies that generate action sequences; world models and hierarchical planners can add foresight and long-horizon structure. Researchers evaluate these methods in simulation suites such as LIBERO, CALVIN, RoboTwin, and navigation benchmarks, as well as on physical robots, with growing attention to memory, contact, safety, and recovery from failure. A central tension is how to make policies generalize across tasks, robots, and changing conditions while remaining data-efficient, reactive, reliable, and fast enough to deploy.

Latest papers

377 papers85 papers in the last four weeks, up 47% on the four weeks before. 0.5% of all new papers.

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA
Jul 29, 2026Tianhang Yang, Yanze Zheng, Junjie Wang +3Robot Policy Learning Expert Routing
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Lab, Shenzhen, China
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
Jul 28, 2026Simple AI, :, Yuteng Wei +16Robot Policy Learning Robot Manipulation Datasets
Simple AI
P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning
Jul 28, 2026Liyun Yan, Jianming Ma, Yang Zhang +5Variational Autoencoders Robot Policy Learning
Shanghai Jiao Tong University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Tongji University, Shanghai, China +1
PAC-DP: PAC-Bayesian Diffusion Policy Learning
Jul 27, 2026Mohammad Hasan Yeganegi, Dian Yu, Andrea Del Prete +2PAC-Bayesian Generalization Bounds Robot Policy Learning
Department of Industrial Engineering, University of Trento, Italy. · Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM), Germany.
LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments
Jul 27, 2026Pei Liu, Nan Zheng, Lang Zhang +8Robot Policy Learning World Models for Robotics
1The Hong Kong University of Science and Technology (Guangzhou) · 2The Hong Kong University of Science and Technology · 3Leapmotor +1
PRISM: Polynomial Representations for Interaction-Structured Motor Control
Jul 26, 2026Seung Hyun Lee, Stella X. YuRobotic Control RL for Robotics
University of Michigan
Robostral Navigate
Jul 22, 2026Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra +273Vision-Language Navigation Robot Navigation
Emergent Compositional Skills in Mixture-of-Experts VLAs
Jul 22, 2026Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss +3Robot Policy Learning Robot Skill Learning
Department of Computer Science, Princeton University, Princeton, NJ, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA
When to Plan: Learning to Select Between Reactive Control and Deliberative Planning
Jul 17, 2026Adam Labiosa, Josiah P. HannaRobot Policy Learning Robotic RL
Department of Computer Sciences, University of Wisconsin–Madison, USA
Learning Agile Navigation in Crowded Environments for Quadruped Robots
Jul 16, 2026Shuyu Wu, Zeyu Liu, Tianbao Zhang +6Robot Policy Learning Robot Navigation
Shanghai Jiao Tong University, Shanghai 200240, China · State Key Laboratory of High-end Heavy-load Robots, Midea Group, Foshan 528300, China
Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment
Jul 15, 2026Boyuan Wang, Zhenyuan Zhang, Zhiqin Yang +16Robot Policy Learning Robotic Data Collection
GigaAI · University of Chinese Academy of Sciences · Hong Kong University of Science and Technology +6
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
Jul 15, 2026GigaWorld Team, Angen Ye, Angyuan Ma +26Robot Policy Learning World Model Learning
GigaAI Tsinghua University
An Empirical Study on Stage-Information Interfaces for VLA Fine-Tuning
Jul 15, 2026Yingwei JiRobot Policy Learning Long-Horizon Robotic Manipulation
EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation
Jul 13, 2026Yuecheng Xu, Tong Yang, Jingkai Jia +3Latent Action Learning Robot Policy Learning
College of Intelligent Robotics and Advanced Manufacturing, Fudan University · Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University · TeleAI, China Telecom
WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos
Jul 13, 2026Jiahao Liu, Yupeng Zheng, Zhongpu Xia +10Latent Action Learning Robot Policy Learning
CASIA · Anyverse Dynamics · UCAS +2
Learning to Navigate with Minimal Parameters: Decomposing Visual Navigation Through Closed-Form Geometric Interfaces
Jul 13, 2026Edward Beng Wai Tan, Siew-Kei LamVisual Navigation Robot Policy Learning
College of Computing and Data Science, Nanyang Technological University, Singapore.
PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation
Jul 11, 2026Shibo Li, Zhongcheng Wang, Jiahe Cao +2Constrained Motion Planning Robot Policy Learning
School of Automation, Northwestern Polytechnical University, Xi’an, China · Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi SE45 05, United Arab Emirates
B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations
Jul 10, 2026Xiaoshen Han, Haoyu Xiong, Haonan Chen +4Robot Policy Learning Robotic Manipulation
1Harvard · 2MIT · 3UT Austin
Implicit Behavior Coordination from Sub-Task Demonstrations by Exploiting Overlap-Induced Multimodality
Jul 10, 2026Ahmed Shokry, Usama Ahmed Siddiquie, Sicong Pan +1Robot Policy Learning Long-Horizon Robotic Manipulation
Humanoid Robots Lab and Center for Robotics, University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany
FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
Jul 9, 2026Michael Murray, Daphne Chen, Simran Bagaria +7Latent Action Learning Robot Policy Learning
1Microsoft Research · University of Washington · 2Microsoft +1
PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
Jul 8, 2026Zezeng Li, Enda Xiang, Thuy Tran +3Robot Policy Learning Test-Time Adaptation
Ecole Centrale de Lyon, France · Beihang University, China
RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
Jul 7, 2026Hanan Gani, Tejal Kulkarni, Madhoolika Chodavarapu +2Robot Policy Learning Robot Skill Learning
University of California, San Diego, CA 92093, USA
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
Jul 6, 2026Kaiyuan Chen, Shuangyu Xie, Letian Fu +21Robot Policy Learning Graph-Based Planning
University of California, Berkeley · Carnegie Mellon University · Bosch +1
Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity
Jul 6, 2026Che-Sang Park, Junsu Ha, Jianlong Fu +1Robot Policy Learning Diffusion-Based Planning
Robotics Laboratory, Seoul National University, Seoul, South Korea · Microsoft Research Asia, Beijing, China
XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
Jul 5, 2026Iok Tong Lei, Ying Jie Yap, Wei Huang +5Robot Policy Learning Language-Conditioned Robot Manipulation
Department of Computer Science and Technology, Tsinghua University, Beijing, China. · National College for Excellent Engineers, Beihang University, Beijing, China. · Independent Researcher +1
Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics
Jul 2, 2026Michael Anoruo, Xiaoyu Tian, Abhishek Rathod +5RL Control Robot Policy Learning
Carnegie Mellon University · Artificial Intelligence Integration Center
Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
Jul 2, 2026Shenghui Zhang, YuXuan Gao, Songwei Zhao +3Robot Policy Learning UAV Navigation
BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer
Jul 1, 2026Yunfu Deng, Josiah P. HannaZero-Shot Learning Robot Policy Learning
Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI 53706 USA
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
Jul 1, 2026Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski +1Robot Policy Learning Robot Policy Adaptation
Carnegie Mellon University
ASPIRE: Agentic /Skills Discovery for Robotics
Jun 30, 2026Runyu Lu, Yubo Wu, Ethan Kou +13Robot Policy Learning Long-Horizon Robotic Manipulation
NVIDIA · UMich · UIUC +2

Jul 29, 2026J/K move · Enter open · S save

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA

Tianhang Yang, Yanze Zheng, Junjie Wang, Wei-Bin Kou+2

Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Lab, Shenzhen, China

Robot Policy Learning Expert Routing VLMs for Robotics

Open paper AskPDF arXiv

While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across manipulation tasks and, even worse, the unavailability of the kinematic signals at inference time. In this work, we first observe that most semantically distinct manipulation tasks reduce to multiple kinematic archetypes. Motivated by this finding, we propose Kinematics-supervised explicit routing (KinRT), a new paradigm that shifts from implicit, observation-driven expert routing to explicit, kinematics-guided expert dispatching. Specifically, we perform kinematic clustering on action trajectories into multiple kinematically coherent groups, whose IDs serve as ground truth to supervise the training of the router; at inference time, the router dispatches experts only using visual-language observations, without any reliance on action kinematics. KinRT actually introduces an asymmetric bridging mechanism that distills the task kinematics from the action space in training into the observation space at inference. In addition, to assess KinRT's cross-platform generalization, we build an economical, Do-It-Yourself robot (DIYRobot) platform from scratch using 3D-print technology (

<

2,000USD). Extensive experiments demonstrate KinRT's superiority over both dense and MoE-featured VLAs by more than 23.26% on RoboTwin benchmark and 20.27% on our introduced DIYRobot platform. Our code and DIYRobot platform will be open-sourced.