Open AccessPosted Content
Learning for Safety-Critical Control with Control Barrier Functions.
TLDR
A machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system, ultimately achieving safe behavior.Abstract:
Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.read more
Citations
More filters
Journal ArticleDOI
Safe Reinforcement Learning for High-speed Autonomous Racing
Journal ArticleDOI
Towards Explainability in Modular Autonomous Vehicle Software
TL;DR: In this paper , the authors focus on explainability and interpretability in the design and optimization of separate Autonomous Vehicle modules including Perception, Planning, and Control, and provide positioning on how researchers could consider incorporating explainability in design and optimisation of autonomous vehicle modules including perception, planning, and control.
Learning Geometric Constraints for Safe Robot Interactions
TL;DR: A novel type of Signed Distance Field (SDF), which is a single neural implicit function and can compute smooth distance field and define dynamic geometric constraints at any scale, is proposed, which can achieve great efficacy in the field of robot safety.
Journal ArticleDOI
District cooling system control for providing regulation services based on safe reinforcement learning with barrier functions
TL;DR: Wang et al. as discussed by the authors proposed a safe deep reinforcement learning (DRL) control method for a district cooling system (DCS) to provide regulation services, which is model-free and adaptive to uncertainties from regulation signals and cooling demands.
Proceedings ArticleDOI
Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning
Wenli Xiao,John M. Dolan +1 more
TL;DR: In this article , a model-based dynamic shielding (MBDS) is proposed for multi-agent reinforcement learning, which enables efficient synthesis of shields to monitor agents in complex environments without coordination overheads.
References
More filters
Journal ArticleDOI
Reinforcement learning in robotics: A survey
TL;DR: This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
Journal ArticleDOI
Survey paper: Set invariance in control
TL;DR: An overview of the literature concerning positively invariant sets and their application to the analysis and synthesis of control systems is provided.
Book
Differential Equations and Dynamical Systems
TL;DR: In this paper, the Third Edition of the Third edition of Linear Systems: Local Theory and Nonlinear Systems: Global Theory (LTLT) is presented, along with an extended version of the second edition.
Book
A Distribution-Free Theory of Nonparametric Regression
TL;DR: How to Construct Nonparametric Regression Estimates * Lower Bounds * Partitioning Estimates * Kernel Estimates * k-NN Estimates * Splitting the Sample * Cross Validation * Uniform Laws of Large Numbers
Book
Nonlinear Systems: Analysis, Stability, and Control
TL;DR: In this article, the authors compare Linear vs. Nonlinear Control of Differential Geometry with Linearization by State Feedback (LSF) by using Linearization and Geometric Non-linear Control (GNC).