The field of autonomous systems and control is rapidly advancing, with a focus on developing more efficient, safe, and adaptive control strategies. Recent developments have seen a shift towards combining model-based control with learning-based approaches, such as reinforcement learning, to improve performance in complex and dynamic environments. Additionally, there is a growing interest in developing control strategies that can handle non-convex domains, uncertain systems, and high-dimensional state spaces. Notable papers in this area include: Learning Safety for Obstacle Avoidance via Control Barrier Functions, which proposes a novel approach to obstacle avoidance using control barrier functions and neural networks. Spatial Envelope MPC: High Performance Driving without a Reference, which presents a new framework for high-performance driving without the need for a predefined reference trajectory.
Advances in Autonomous Systems and Control
Sources
Hierarchical Reinforcement Learning with Low-Level MPC for Multi-Agent Control
Real-Time Planning and Control with a Vortex Particle Model for Fixed-Wing UAVs in Unsteady Flows
Learning Safety for Obstacle Avoidance via Control Barrier Functions
Spatial Envelope MPC: High Performance Driving without a Reference
Number Adaptive Formation Flight Planning via Affine Deformable Guidance in Narrow Environments
Robust Near-Optimal Nonlinear Target Enclosing Guidance
Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
Trajectory Planning Using Safe Ellipsoidal Corridors as Projections of Orthogonal Trust Regions
Dispersion Formation Control: from Geometry to Distribution
Zonotope-Based Elastic Tube Model Predictive Control
Control and Navigation of a 2-D Electric Rocket
An effective control of large systems of active particles: An application to evacuation problem
C-3TO: Continuous 3D Trajectory Optimization on Neural Euclidean Signed Distance Fields
Adversarial Pursuits in Cislunar Space