The field of robotics is witnessing significant advancements in motion planning and control, driven by the need for safe, efficient, and adaptive navigation in complex environments. Researchers are exploring innovative approaches to address the challenges posed by dynamic obstacles, uncertainty, and non-linear dynamics. A key trend is the integration of machine learning and model predictive control to enable robots to anticipate and respond to changing situations. Another area of focus is the development of novel control frameworks for soft robots, which offer advantages in terms of flexibility and compliance. Notable papers in this area include: * The paper on Learning-Based Modeling of Soft Actuators Using Euler Spiral-Inspired Curvature, which presents a data-driven approach to modeling soft continuum actuators. * The paper on Diffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations, which proposes a framework for robust extrapolation of learned skills in complex environments.
Advancements in Robot Motion Planning and Control
Sources
Learning-Based Modeling of Soft Actuators Using Euler Spiral-Inspired Curvature
Diffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations
Trajectory Planning with Model Predictive Control for Obstacle Avoidance Considering Prediction Uncertainty
Efficient COLREGs-Compliant Collision Avoidance using Turning Circle-based Control Barrier Function
A Time-dependent Risk-aware distributed Multi-Agent Path Finder based on A*
Robot Motion Planning using One-Step Diffusion with Noise-Optimized Approximate Motions
Tendon-Actuated Concentric Tube Endonasal Robot (TACTER)
Kinodynamic Trajectory Following with STELA: Simultaneous Trajectory Estimation & Local Adaptation
A Koopman Operator-based NMPC Framework for Mobile Robot Navigation under Uncertainty
Characterizing gaussian mixture of motion modes for skid-steer state estimation
Future-Oriented Navigation: Dynamic Obstacle Avoidance with One-Shot Energy-Based Multimodal Motion Prediction
Multi-segment Soft Robot Control via Deep Koopman-based Model Predictive Control
Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations