APPLR: Adaptive Planner Parameter Learning from Reinforcement
This addresses the need for more adaptive and efficient navigation systems in robotics, reducing reliance on expert tuning and human demonstrations, though it is incremental as it builds on existing RL methods.
The paper tackles the problem of classical navigation systems requiring manual parameter tuning for new environments by introducing APPLR, which uses reinforcement learning to adaptively select parameters, and shows it outperforms both fixed hand-tuned parameters and demonstration-based tuning in simulated and physical experiments.
Classical navigation systems typically operate using a fixed set of hand-picked parameters (e.g. maximum speed, sampling rate, inflation radius, etc.) and require heavy expert re-tuning in order to work in new environments. To mitigate this requirement, it has been proposed to learn parameters for different contexts in a new environment using human demonstrations collected via teleoperation. However, learning from human demonstration limits deployment to the training environment, and limits overall performance to that of a potentially-suboptimal demonstrator. In this paper, we introduce APPLR, Adaptive Planner Parameter Learning from Reinforcement, which allows existing navigation systems to adapt to new scenarios by using a parameter selection scheme discovered via reinforcement learning (RL) in a wide variety of simulation environments. We evaluate APPLR on a robot in both simulated and physical experiments, and show that it can outperform both a fixed set of hand-tuned parameters and also a dynamic parameter tuning scheme learned from human demonstration.