The field of autonomous systems is witnessing significant advancements in safe and robust control, with a focus on ensuring the reliability and efficiency of controllers in complex environments. Researchers are exploring innovative approaches to handle disturbances, uncertainties, and safety constraints, leveraging techniques such as control barrier functions, model predictive control, and neural networks. These developments aim to provide formal guarantees for safety and performance, enabling the widespread adoption of autonomous systems in various applications. Notably, the integration of machine learning and control theory is leading to more scalable and data-efficient solutions. Some noteworthy papers in this area include: The work on Spacecraft Safe Robust Control Using Implicit Neural Representation, which proposes a novel framework for safe proximity operations using neural signed distance functions. The introduction of CPED-NCBFs, a conformal prediction-based verification strategy for neural control barrier functions, which enhances the reliability of learned safety certificates.
Safe and Robust Control in Autonomous Systems
Sources
Spacecraft Safe Robust Control Using Implicit Neural Representation for Geometrically Complex Targets in Proximity Operations
Safety Certification in the Latent space using Control Barrier Functions and World Models
Safe and Performant Controller Synthesis using Gradient-based Model Predictive Control and Control Barrier Functions
Fixed time convergence guarantees for Higher Order Control Barrier Functions
Reference-Free Iterative Learning Model Predictive Control with Neural Certificates
Corridor-based Adaptive Control Barrier and Lyapunov Functions for Safe Mobile Robot Navigation
CPED-NCBFs: A Conformal Prediction for Expert Demonstration-based Neural Control Barrier Functions
The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents
Automating Capacitor Part Selection with Dual-Objective Optimization
Multi-objective Portfolio Optimization Via Gradient Descent
Falconry-like palm landing by a flapping-wing drone based on the human gesture interaction and distance-aware flight planning
Safety Assurance for Quadrotor Kinodynamic Motion Planning
A Step-by-step Guide on Nonlinear Model Predictive Control for Safe Mobile Robot Navigation
Maneuvering-based Dynamic Thrust Allocation for Fully-Actuated Vessels