Mobility-Aware Computation Offloading for Swarm Robotics using Deep Reinforcement Learning
This work addresses energy and computation constraints in swarm robotics, enabling more efficient automation for tasks like dirty, dangerous, and dull operations, though it appears incremental as it builds on existing offloading and DRL methods.
The paper tackles the problem of limited computation and energy in swarm robotics by proposing a mobility-aware deep reinforcement learning model for computation offloading to mobile edge computing, resulting in meeting delay requirements and guaranteeing computation precision while minimizing robot energy usage.
Swarm robotics is envisioned to automate a large number of dirty, dangerous, and dull tasks. Robots have limited energy, computation capability, and communication resources. Therefore, current swarm robotics have a small number of robots, which can only provide limited spatio-temporal information. In this paper, we propose to leverage the mobile edge computing to alleviate the computation burden. We develop an effective solution based on a mobility-aware deep reinforcement learning model at the edge server side for computing scheduling and resource. Our results show that the proposed approach can meet delay requirements and guarantee computation precision by using minimum robot energy.