Propagating State Uncertainty Through Trajectory Forecasting

TL;DR

This paper introduces a novel method for incorporating perceptual state uncertainty into trajectory forecasting, improving the calibration of predictions by propagating upstream perceptual uncertainties.

Contribution

The paper presents a new statistical distance-based loss function and a framework to effectively propagate perceptual uncertainty through trajectory predictions.

Findings

Enhanced calibration of trajectory predictions with uncertainty propagation

Effective in both simulated and real-world datasets

Produces more reliable and less overconfident forecasts

Abstract

Uncertainty pervades through the modern robotic autonomy stack, with nearly every component (e.g., sensors, detection, classification, tracking, behavior prediction) producing continuous or discrete probabilistic distributions. Trajectory forecasting, in particular, is surrounded by uncertainty as its inputs are produced by (noisy) upstream perception and its outputs are predictions that are often probabilistic for use in downstream planning. However, most trajectory forecasting methods do not account for upstream uncertainty, instead taking only the most-likely values. As a result, perceptual uncertainties are not propagated through forecasting and predictions are frequently overconfident. To address this, we present a novel method for incorporating perceptual state uncertainty in trajectory forecasting, a key component of which is a new statistical distance-based loss function which encourages predicting uncertainties that better match upstream perception. We evaluate our approach both in illustrative simulations and on large-scale, real-world data, demonstrating its efficacy in propagating perceptual state uncertainty through prediction and producing more calibrated predictions.