safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning

• URL: http://arxiv.org/abs/2109.06325v1
• Date: Mon, 13 Sep 2021 21:09:28 GMT
• Title: safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning
• Authors: Zhaocong Yuan, Adam W. Hall, Siqi Zhou, Lukas Brunke, Melissa Greeff, Jacopo Panerati, Angela P. Schoellig (University of Toronto Institute for Aerospace Studies, University of Toronto Robotics Institute, Vector Institute for Artificial Intelligence)
• Abstract summary: We propose a new open-source benchmark suite, called safe-control-gym. Our starting point is OpenAI's Gym API, which is one of the de facto standard in reinforcement learning research. We show how to use safe-control-gym to quantitatively compare the control performance, data efficiency, and safety of multiple approaches.
• Score: 3.9258421820410225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, reinforcement learning and learning-based control -- as well as the study of their safety, crucial for deployment in real-world robots -- have gained significant traction. However, to adequately gauge the progress and applicability of new results, we need the tools to equitably compare the approaches proposed by the controls and reinforcement learning communities. Here, we propose a new open-source benchmark suite, called safe-control-gym. Our starting point is OpenAI's Gym API, which is one of the de facto standard in reinforcement learning research. Yet, we highlight the reasons for its limited appeal to control theory researchers -- and safe control, in particular. E.g., the lack of analytical models and constraint specifications. Thus, we propose to extend this API with (i) the ability to specify (and query) symbolic models and constraints and (ii) introduce simulated disturbances in the control inputs, measurements, and inertial properties. We provide implementations for three dynamic systems -- the cart-pole, 1D, and 2D quadrotor -- and two control tasks -- stabilization and trajectory tracking. To demonstrate our proposal -- and in an attempt to bring research communities closer together -- we show how to use safe-control-gym to quantitatively compare the control performance, data efficiency, and safety of multiple approaches from the areas of traditional control, learning-based control, and reinforcement learning.

Related papers

• Reinforcement Learning with Ensemble Model Predictive Safety Certification [2.658598582858331]
  unsupervised exploration prevents the deployment of reinforcement learning algorithms on safety-critical tasks. We propose a new algorithm that combines model-based deep reinforcement learning with tube-based model predictive control to correct the actions taken by a learning agent. Our results show that we can achieve significantly fewer constraint violations than comparable reinforcement learning methods.
  arXiv  Detail & Related papers  (2024-02-06T17:42:39Z)
• Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms [5.7648266677851865]
  We introduce controlgym, a library of 36 industrial control settings, and ten infinite-dimensional partial differential equation (PDE)-based control problems. controlgym is integrated within the OpenAI Gym/Gymnasium framework.
  arXiv  Detail & Related papers  (2023-11-30T17:34:05Z)
• In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States [84.24300005271185]
  We propose a control filter that wraps any reference policy and effectively encourages the system to stay in-distribution with respect to offline-collected safe demonstrations. Our method is effective for two different visuomotor control tasks in simulation environments, including both top-down and egocentric view settings.
  arXiv  Detail & Related papers  (2023-01-27T22:28:19Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• Sparsity in Partially Controllable Linear Systems [56.142264865866636]
  We study partially controllable linear dynamical systems specified by an underlying sparsity pattern. Our results characterize those state variables which are irrelevant for optimal control.
  arXiv  Detail & Related papers  (2021-10-12T16:41:47Z)
• Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning [3.9258421820410225]
  We review the recent advances made in using machine learning to achieve safe decision making under uncertainties. Our review includes: learning-based control approaches that safely improve performance by learning the uncertain dynamics. We highlight some of the open challenges that will drive the field of robot learning in the coming years.
  arXiv  Detail & Related papers  (2021-08-13T14:22:02Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)
• Model-Reference Reinforcement Learning for Collision-Free Tracking Control of Autonomous Surface Vehicles [1.7033108359337459]
  The proposed control algorithm combines a conventional control method with reinforcement learning to enhance control accuracy and intelligence. Thanks to reinforcement learning, the overall tracking controller is capable of compensating for model uncertainties and achieving collision avoidance.
  arXiv  Detail & Related papers  (2020-08-17T12:15:15Z)
• Data-driven Koopman Operators for Model-based Shared Control of Human-Machine Systems [66.65503164312705]
  We present a data-driven shared control algorithm that can be used to improve a human operator's control of complex machines. Both the dynamics and information about the user's interaction are learned from observation through the use of a Koopman operator. We find that model-based shared control significantly improves task and control metrics when compared to a natural learning, or user only, control paradigm.
  arXiv  Detail & Related papers  (2020-06-12T14:14:07Z)
• Model-Reference Reinforcement Learning Control of Autonomous Surface Vehicles with Uncertainties [1.7033108359337459]
  The proposed control combines a conventional control method with deep reinforcement learning. With the reinforcement learning, we can directly learn a control law to compensate for modeling uncertainties. In comparison with traditional deep reinforcement learning methods, our proposed learning-based control can provide stability guarantees and better sample efficiency.
  arXiv  Detail & Related papers  (2020-03-30T22:02:13Z)

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.