ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties

TL;DR

ELLIPSE is a novel evidential learning method that enhances the robustness and reliability of waypoint prediction and uncertainty estimation for mobile robots in open-world environments, especially under distribution shifts.

Contribution

It introduces a multivariate evidential regression approach with domain augmentation and recalibration techniques to improve robustness and uncertainty reliability in waypoint prediction.

Findings

Improves task success rate in staircase waypoint prediction.

Enhances uncertainty coverage under environment shifts.

Outperforms baseline methods in real-world evaluations.

Abstract

Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distribution shifts: the policy can become dangerously overconfident in unfamiliar states. In this paper, we present \textit{ELLIPSE}, a method building on multivariate deep evidential regression to output waypoints and multivariate Student-t predictive distributions in a single forward pass. To reduce covariate-shift-induced overconfidence under viewpoint and pose perturbations near expert trajectories, we introduce a lightweight domain augmentation procedure that synthesizes plausible viewpoint/pose variations without collecting additional demonstrations. To improve uncertainty reliability under environment/domain shift (e.g., unseen staircases), we apply a post-hoc isotonic recalibration on probability integral transform (PIT) values so that prediction sets remain plausible during deployment. We ground the discussion and experiments in staircase waypoint prediction, where obtaining robust waypoint and uncertainty is pivotal. Extensive real world evaluations show that \textit{ELLIPSE} improves both task success rate and uncertainty coverage compared to baselines.