Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users' Trajectories

TL;DR

This paper introduces a probabilistic method for forecasting vulnerable road users' trajectories by integrating past movements, 3D poses, and semantic scene maps, evaluated on real urban traffic data.

Contribution

The novel approach combines 3D pose data and semantic maps for improved probabilistic trajectory forecasting of VRUs, with a focus on reliability and situational adaptation.

Findings

Poses positively influence forecast accuracy.

Semantic maps enable situationally adaptive probability distributions.

The method outperforms Gaussian-based forecasts in reliability.

Abstract

In this article, an approach for probabilistic trajectory forecasting of vulnerable road users (VRUs) is presented, which considers past movements and the surrounding scene. Past movements are represented by 3D poses reflecting the posture and movements of individual body parts. The surrounding scene is modeled in the form of semantic maps showing, e.g., the course of streets, sidewalks, and the occurrence of obstacles. The forecasts are generated in grids discretizing the space and in the form of arbitrary discrete probability distributions. The distributions are evaluated in terms of their reliability, sharpness, and positional accuracy. We compare our method with an approach that provides forecasts in the form of Gaussian distributions and discuss the respective advantages and disadvantages. Thereby, we investigate the impact of using poses and semantic maps. With a technique called spatial label smoothing, our approach achieves reliable forecasts. Overall, the poses have a positive impact on the forecasts. The semantic maps offer the opportunity to adapt the probability distributions to the individual situation, although at the considered forecasted time horizon of 2.52 s they play a minor role compared to the past movements of the VRU. Our method is evaluated on a dataset recorded in inner-city traffic using a research vehicle. The dataset is made publicly available.