APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback

TL;DR

APPLE introduces a new method for robot navigation that learns to adapt planner parameters using real-time evaluative feedback, reducing user control demands and improving navigation performance.

Contribution

It proposes a novel evaluative feedback-based learning approach for adaptive planner parameter tuning, eliminating the need for full teleoperation during learning.

Findings

APPLE outperforms static default parameters in simulations and real-world tests.

It surpasses previous methods that require full teleoperation or richer interaction modalities.

The approach enhances robot navigation efficiency and safety.

Abstract

Classical autonomous navigation systems can control robots in a collision-free manner, oftentimes with verifiable safety and explainability. When facing new environments, however, fine-tuning of the system parameters by an expert is typically required before the system can navigate as expected. To alleviate this requirement, the recently-proposed Adaptive Planner Parameter Learning paradigm allows robots to \emph{learn} how to dynamically adjust planner parameters using a teleoperated demonstration or corrective interventions from non-expert users. However, these interaction modalities require users to take full control of the moving robot, which requires the users to be familiar with robot teleoperation. As an alternative, we introduce \textsc{apple}, Adaptive Planner Parameter Learning from \emph{Evaluative Feedback} (real-time, scalar-valued assessments of behavior), which represents a less-demanding modality of interaction. Simulated and physical experiments show \textsc{apple} can achieve better performance compared to the planner with static default parameters and even yield improvement over learned parameters from richer interaction modalities.