Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications

• URL: http://arxiv.org/abs/2404.09080v2
• Date: Wed, 06 Nov 2024 10:23:59 GMT
• Title: Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications
• Authors: Puze Liu, Haitham Bou-Ammar, Jan Peters, Davide Tateo,
• Abstract summary: We show how we can impose complex safety constraints on learning-based robotics systems in a principled manner. Our approach is based on the concept of the Constraint Manifold, representing the set of safe robot configurations. We demonstrate the method's effectiveness in a real-world Robot Air Hockey task.
• Score: 21.98309272057848
• License:
• Abstract: Integrating learning-based techniques, especially reinforcement learning, into robotics is promising for solving complex problems in unstructured environments. However, most existing approaches are trained in well-tuned simulators and subsequently deployed on real robots without online fine-tuning. In this setting, extensive engineering is required to mitigate the sim-to-real gap, which can be challenging for complex systems. Instead, learning with real-world interaction data offers a promising alternative: it not only eliminates the need for a fine-tuned simulator but also applies to a broader range of tasks where accurate modeling is unfeasible. One major problem for on-robot reinforcement learning is ensuring safety, as uncontrolled exploration can cause catastrophic damage to the robot or the environment. Indeed, safety specifications, often represented as constraints, can be complex and non-linear, making safety challenging to guarantee in learning systems. In this paper, we show how we can impose complex safety constraints on learning-based robotics systems in a principled manner, both from theoretical and practical points of view. Our approach is based on the concept of the Constraint Manifold, representing the set of safe robot configurations. Exploiting differential geometry techniques, i.e., the tangent space, we can construct a safe action space, allowing learning agents to sample arbitrary actions while ensuring safety. We demonstrate the method's effectiveness in a real-world Robot Air Hockey task, showing that our method can handle high-dimensional tasks with complex constraints. Videos of the real robot experiments are available on the project website (https://puzeliu.github.io/TRO-ATACOM).

Related papers

• Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning [17.856459823003277]
  Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. In this paper, we bridge the gap by extending the safe exploration method, ATACOM, with learnable constraints.
  arXiv  Detail & Related papers  (2024-09-18T15:08:41Z)
• Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning [20.158498233576143]
  Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex motions under intricate constraints. This paper addresses this limitation by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization.
  arXiv  Detail & Related papers  (2024-08-26T07:44:53Z)
• Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models [81.55156507635286]
  Legged robots are physically capable of navigating a diverse variety of environments and overcoming a wide range of obstructions. Current learning methods often struggle with generalization to the long tail of unexpected situations without heavy human supervision. We propose a system, VLM-Predictive Control (VLM-PC), combining two key components that we find to be crucial for eliciting on-the-fly, adaptive behavior selection.
  arXiv  Detail & Related papers  (2024-07-02T21:00:30Z)
• ABNet: Attention BarrierNet for Safe and Scalable Robot Learning [58.4951884593569]
  Barrier-based method is one of the dominant approaches for safe robot learning. We propose Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving.
  arXiv  Detail & Related papers  (2024-06-18T19:37:44Z)
• Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration [8.343657309038285]
  Reinforcement Learning is a powerful framework for developing such robot controllers. We propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers.
  arXiv  Detail & Related papers  (2023-08-04T16:55:00Z)
• Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance [71.36749876465618]
  We describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples. experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world.
  arXiv  Detail & Related papers  (2022-12-19T22:50:40Z)
• Safe reinforcement learning of dynamic high-dimensional robotic tasks: navigation, manipulation, interaction [31.553783147007177]
  In reinforcement learning, safety is even more fundamental for exploring an environment without causing any damage. This paper introduces a new formulation of safe exploration for reinforcement learning of various robotic tasks. Our approach applies to a wide class of robotic platforms and enforces safety even under complex collision constraints learned from data.
  arXiv  Detail & Related papers  (2022-09-27T11:23:49Z)
• Dual-Arm Adversarial Robot Learning [0.6091702876917281]
  We propose dual-arm settings as platforms for robot learning. We will discuss the potential benefits of this setup as well as the challenges and research directions that can be pursued.
  arXiv  Detail & Related papers  (2021-10-15T12:51:57Z)
• Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms [60.59764170868101]
  Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. We formulate it as a few-shot meta-learning problem where the goal is to find a model that captures the common structure shared across different robotic platforms. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots.
  arXiv  Detail & Related papers  (2021-03-05T14:16:20Z)
• Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera [58.720142291102135]
  We use a simulator to learn the peg-hole insertion problem and then transfer the learned model to the real robot. We show that the transferred policy, which only takes RGB-D and joint information (proprioception) can perform well on the real robot.
  arXiv  Detail & Related papers  (2020-05-29T05:58:54Z)
• The Ingredients of Real-World Robotic Reinforcement Learning [71.92831985295163]
  We discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world. We propose a particular instantiation of such a system, using dexterous manipulation as our case study. We demonstrate that our complete system can learn without any human intervention, acquiring a variety of vision-based skills with a real-world three-fingered hand.
  arXiv  Detail & Related papers  (2020-04-27T03:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.