mlsanityData to 14 Oct 2026

Risk-Aware Reinforcement Learning for Mobile Manipulation

arXiv 2603.04579 ↗First posted 4 Mar 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

For robots to successfully transition from lab settings to everyday environments, they must begin to reason about the risks associated with their actions and make informed, risk-aware decisions. This is particularly true for robots performing mobile manipulation tasks, which involve both interacting with and navigating within dynamic, unstructured spaces. However, existing whole-body controllers for mobile manipulators typically lack explicit mechanisms for risk-sensitive decision-making under uncertainty. To our knowledge, we are the first to (i) learn risk-aware visuomotor policies for mobile manipulation conditioned on egocentric depth observations with runtime-adjustable risk sensitivity, and (ii) show risk-aware behaviours can be transferred through Imitation Learning (IL) to a visuomotor policy conditioned on egocentric depth observations. Our method achieves this by first training a privileged teacher policy using Distributional Reinforcement Learning (DRL), with a risk-neutral distributional critic. Distortion risk-metrics are then applied to the critic's predicted return distribution to calculate risk-adjusted advantage estimates used in policy updates to achieve a range of risk-aware behaviours. We then distil teacher policies with IL to obtain risk-aware student policies conditioned on egocentric depth observations. We perform extensive evaluations demonstrating that our trained visuomotor policies exhibit risk-aware behaviour (specifically achieving better worst-case performance) while performing reactive whole-body motions in unmapped environments, leveraging live depth observations for perception.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 26 of its 37 references that are in the map. First posted on arXiv 4 Mar 2026.

Builds on

26 of 37 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning3 Feb
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes7 Aug

Other references · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2018Exploration by Random Network Distillationcited by 993
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  7. 2018Learning Dexterous In-Hand Manipulationcited by 687
  8. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  9. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  10. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  11. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  12. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
12 more
  1. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 229
  2. 2023Extreme Parkour with Legged Robotscited by 164
  3. 2024Visual Whole-Body Control for Legged Loco-Manipulationcited by 62
  4. 2017How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Roboticscited by 59
  5. 2019Quantile QT-Opt for Risk-Aware Vision-Based Robotic Graspingcited by 29
  6. 2024SPIN: Simultaneous Perception, Interaction and Navigationcited by 29
  7. 2022One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learningcited by 23
  8. 2023Robust Quadrupedal Locomotion via Risk-Averse Policy Learningcited by 19
  9. 2021A Holistic Approach to Reactive Mobile Manipulationcited by 17
  10. 2023Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learningcited by 14
  11. 2020DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learningcited by 8
  12. 2021Automatic Risk Adaptation in Distributional Reinforcement Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026To Do or Not to Do: Ensuring the Safety of Visuomotor Policies Learned from Demonstrations
  2. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation
  3. 2025Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection
  4. 2024A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learning
  5. 2022Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation
  6. 2025Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
  7. 2024How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation
  8. 2025RISE: Robust Imitation through Stochastic Encoding