MultiXNet: Multiclass Multistage Multimodal Motion Prediction

TL;DR

MultiXNet is an end-to-end multimodal motion prediction system for self-driving vehicles that detects and predicts multiple traffic actor behaviors directly from lidar data, outperforming existing methods.

Contribution

It introduces a novel multimodal, multiclass, multistage approach with trajectory refinement and uncertainty calibration for lidar-based motion prediction.

Findings

Outperforms state-of-the-art methods on real-world datasets

Handles multiple traffic actor classes simultaneously

Provides calibrated probabilistic motion predictions

Abstract

One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future. To address this task we propose MultiXNet, an end-to-end approach for detection and motion prediction based directly on lidar sensor data. This approach builds on prior work by handling multiple classes of traffic actors, adding a jointly trained second-stage trajectory refinement step, and producing a multimodal probability distribution over future actor motion that includes both multiple discrete traffic behaviors and calibrated continuous position uncertainties. The method was evaluated on large-scale, real-world data collected by a fleet of SDVs in several cities, with the results indicating that it outperforms existing state-of-the-art approaches.