Constrained Robot
Constrained robots are robotic systems operating under limitations such as limited battery life, computational power, or physical size, necessitating efficient resource management and task planning. Current research focuses on optimizing energy consumption through techniques like control barrier functions, deep reinforcement learning for task scheduling and computation offloading, and evolutionary algorithms for trajectory optimization. These advancements are crucial for enabling longer operational times, expanding the capabilities of robots in challenging environments (e.g., under-ice exploration, swarm robotics), and improving the efficiency of applications like autonomous agriculture and environmental monitoring.
Papers
Maximum Solar Energy Tracking Leverage High-DoF Robotics System with Deep Reinforcement Learning
Anjie Jiang, Kangtong Mo, Satoshi Fujimoto, Michael Taylor, Sanjay Kumar, Chiotis Dimitrios, Emilia Ruiz
Synthesising Robust Controllers for Robot Collectives with Recurrent Tasks: A Case Study
Till Schnittka (University of Bremen), Mario Gleirscher (University of Bremen)