The field of control and robotics is rapidly advancing with a focus on developing innovative solutions to complex problems. Recent research has explored the application of reinforcement learning, neural networks, and optimization techniques to improve control systems, motion planning, and autonomous decision-making. Notably, the development of model-free and data-driven approaches has shown promise in addressing challenges such as uncertainty, nonlinearity, and real-time control. Furthermore, the integration of machine learning and control theory has enabled the creation of more robust, adaptive, and efficient control systems. Overall, the field is moving towards the development of more intelligent, autonomous, and resilient systems. Noteworthy papers include: The paper on 'Hyperproperty-Constrained Secure Reinforcement Learning' which proposes an approach for learning security-aware optimal policies using dynamic Boltzmann softmax RL while satisfying HyperTWTL constraints. The paper on 'Neural Co-state Projection Regulator' which introduces a model-free learning-based optimal control framework that is grounded in Pontryagin's Minimum Principle and capable of solving quadratic regulator problems in nonlinear control-affine systems with input constraints.
Advancements in Control and Robotics
Sources
Hyperproperty-Constrained Secure Reinforcement Learning
Data-Driven Motion Planning for Uncertain Nonlinear Systems
RL as Regressor: A Reinforcement Learning Approach for Function Approximation
Adaptive Compensation of Nonlinear Friction in Mechanical Systems Without Velocity Measurement
Neural Co-state Projection Regulator: A Model-free Paradigm for Real-time Optimal Control with Input Constraints
Real-World Evaluation of Protocol-Compliant Denial-of-Service Attacks on C-V2X-based Forward Collision Warning Systems
Modeling and Simulation of an Active Quarter Car Suspension with a Robust LQR Controller under Road Disturbance and Parameter Uncertainty
Neural Approximators for Low-Thrust Trajectory Transfer Cost and Reachability
Context-aware Risk Assessment and Its Application in Autonomous Driving
Optimal Trajectory Planning in a Vertically Undulating Snake Locomotion using Contact-implicit Optimization
A Robust Cooperative Vehicle Coordination Framework for Intersection Crossing
Residual Neural Terminal Constraint for MPC-based Collision Avoidance in Dynamic Environments
Online Learning for Vibration Suppression in Physical Robot Interaction using Power Tools
Control Closure Certificates
Optimization of sliding control parameters for a 3-dof robot arm using genetic algorithm (GA)
DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving
Symmetric Behavior Regularization via Taylor Expansion of Symmetry
Incorporating Stochastic Models of Controller Behavior into Kinodynamic Efficiently Adaptive State Lattices for Mobile Robot Motion Planning in Off-Road Environments
Reliable and Real-Time Highway Trajectory Planning via Hybrid Learning-Optimization Frameworks
Passive nonlinear FIR filters for data-driven control
Robust adaptive fuzzy sliding mode control for trajectory tracking for of cylindrical manipulator
Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling