The field of autonomous systems is witnessing significant advancements in safe and efficient control. Recent developments focus on ensuring the safety and reliability of autonomous systems, particularly in complex and dynamic environments. One notable direction is the integration of formal methods and machine learning techniques to provide guarantees on system behavior. This includes the use of control barrier functions, safety filters, and predictive models to prevent accidents and ensure compliance with safety regulations. Another area of research is the development of more efficient and adaptive control algorithms, such as model predictive control and reinforcement learning, which can handle uncertain and changing environments. Noteworthy papers in this area include 'Learning Control Barrier Functions with Deterministic Safety Guarantees' and 'Neural NMPC through Signed Distance Field Encoding for Collision Avoidance', which propose innovative approaches to safety-critical control. Overall, these advancements have the potential to significantly improve the safety and efficiency of autonomous systems, enabling their wider adoption in various applications.
Advancements in Safe and Efficient Control of Autonomous Systems
Sources
SAFE-SMART: Safety Analysis and Formal Evaluation using STL Metrics for Autonomous RoboTs
Event-Chain Analysis for Automated Driving and ADAS Systems: Ensuring Safety and Meeting Regulatory Timing Requirements
Time-aware Motion Planning in Dynamic Environments with Conformal Prediction
How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
PolyOCP.jl -- A Julia Package for Stochastic OCPs and MPC
First-order Sobolev Reinforcement Learning
Data-driven certificates of constraint enforcement and stability for unmodeled, discrete dynamical systems using tree data structures
Data driven synthesis of provable invariant sets via stochastically sampled data
Strong Duality and Dual Ascent Approach to Continuous-Time Chance-Constrained Stochastic Optimal Control
Online Learning-Enhanced High Order Adaptive Safety Control
Reinforcement Learning with $\omega$-Regular Objectives and Constraints
Improved adaptive wind driven optimization algorithm for real-time path planning
Learning Control Barrier Functions with Deterministic Safety Guarantees
Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning
Conformal Safety Monitoring for Flight Testing: A Case Study in Data-Driven Safety Learning
Neural NMPC through Signed Distance Field Encoding for Collision Avoidance
Predictive Safety Shield for Dyna-Q Reinforcement Learning
Bang-Bang Evasion: Its Stochastic Optimality and a Terminal-Set-Based Implementation