Safe learning in robotics: From learning-based control to safe reinforcement learning
The last half decade has seen a steep rise in the number of contributions on safe learning
methods for real-world robotic deployments from both the control and reinforcement learning …
methods for real-world robotic deployments from both the control and reinforcement learning …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Robust control barrier–value functions for safety-critical control
This paper works towards unifying two popular approaches in the safety control community:
Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has …
Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has …
Data-driven safety filters: Hamilton-jacobi reachability, control barrier functions, and predictive methods for uncertain systems
Today's control engineering problems exhibit an unprecedented complexity, with examples
including the reliable integration of renewable energy sources into power grids, safe …
including the reliable integration of renewable energy sources into power grids, safe …
Refining control barrier functions through Hamilton-Jacobi reachability
Safety filters based on Control Barrier Functions (CBFs) have emerged as a practical tool for
the safety-critical control of autonomous systems. These approaches encode safety through …
the safety-critical control of autonomous systems. These approaches encode safety through …
Synthesizing control barrier functions with feasible region iteration for safe reinforcement learning
Safety is a critical concern when applying reinforcement learning to real-world control
problems. A widely used method for ensuring safety is to learn a control barrier function with …
problems. A widely used method for ensuring safety is to learn a control barrier function with …
The Feasibility of Constrained Reinforcement Learning Algorithms: A Tutorial Study
Satisfying safety constraints is a priority concern when solving optimal control problems
(OCPs). Due to the existence of infeasibility phenomenon, where a constraint-satisfying …
(OCPs). Due to the existence of infeasibility phenomenon, where a constraint-satisfying …
Provably safe reinforcement learning: A theoretical and experimental comparison
Ensuring safety of reinforcement learning (RL) algorithms is crucial to unlock their potential
for many real-world tasks. However, vanilla RL does not guarantee safety. In recent years …
for many real-world tasks. However, vanilla RL does not guarantee safety. In recent years …
Constructing control lyapunov-value functions using hamilton-jacobi reachability analysis
In this letter, we seek to build connections between control Lyapunov functions (CLFs) and
Hamilton-Jacobi (HJ) reachability analysis. CLFs have been used extensively in the control …
Hamilton-Jacobi (HJ) reachability analysis. CLFs have been used extensively in the control …
Safe non-stochastic control of control-affine systems: An online convex optimization approach
We study how to safely control nonlinear control-affine systems that are corrupted with
bounded non-stochastic noise, ie, noise that is unknown a priori and that is not necessarily …
bounded non-stochastic noise, ie, noise that is unknown a priori and that is not necessarily …