The field of robotics is witnessing significant developments in control and safety mechanisms. Researchers are exploring innovative approaches to improve the stability, adaptability, and reliability of robotic systems. A key direction is the integration of model predictive control (MPC) and machine learning techniques to enable robots to adapt to changing environments and unexpected disturbances. Another area of focus is the development of safety frameworks that can ensure collision avoidance and maintain safe interaction with humans and the environment. Noteworthy papers in this area include: Mass-Adaptive Admittance Control for Robotic Manipulators, which presents a novel approach to handling objects with unknown masses. Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators, which enables force tracking while guaranteeing passivity. Learning Verifiable Control Policies Using Relaxed Verification, which proposes a method for verifying control policies throughout training to ensure safety guarantees.
Advancements in Robotic Control and Safety
Sources
A Model Predictive Control Approach for Quadrotor Cruise Control
Magnecko: Design and Control of a Quadrupedal Magnetic Climbing Robot
Collision Induced Binding and Transport of Shape Changing Robot Pairs
Haptic-based Complementary Filter for Rigid Body Rotations
Safe Autonomous Environmental Contact for Soft Robots using Control Barrier Functions
Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL
On relaxing the N-Reachability Implicit Requirement in NMPC Design
Distributed model predictive control without terminal cost under inexact distributed optimization
Predictive Synthesis of Control Barrier Functions and its Application to Time-Varying Constraints
Mass-Adaptive Admittance Control for Robotic Manipulators
Anytime Safe Reinforcement Learning
Learning Verifiable Control Policies Using Relaxed Verification
Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators
Subframework-based Bearing Rigidity Maintenance Control in Multirobot Networks
Simultaneous Collision Detection and Force Estimation for Dynamic Quadrupedal Locomotion
Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control