A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks
This work addresses task execution challenges in multi-robot systems, but it appears incremental as it builds on existing optimization and learning methods without claiming major breakthroughs.
The paper tackles the problem of executing prioritized multi-robot tasks by proposing a constrained-optimization framework that encodes tasks as constraints using control Lyapunov functions, with results demonstrated in simulation for coordinated mobile robots.
This paper presents a constrained-optimization formulation for the prioritized execution of learned robot tasks. The framework lends itself to the execution of tasks encoded by value functions, such as tasks learned using the reinforcement learning paradigm. The tasks are encoded as constraints of a convex optimization program by using control Lyapunov functions. Moreover, an additional constraint is enforced in order to specify relative priorities between the tasks. The proposed approach is showcased in simulation using a team of mobile robots executing coordinated multi-robot tasks.