Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Pedestrian motion prediction evaluation for urban autonomous driving

Dmytro Zabolotnii, Yar Muhammad, Naveed Muhammad

TL;DR

This paper analyzes a set of selected methods from the literature, and presents the perspective obtained by integrating them into an existing autonomous-driving software stack - Autoware Mini - and performing experiments in natural urban conditions in Tartu, Estonia to determine the suitability of conventional motion prediction metrics.

Abstract

Pedestrian motion prediction is a key part of the modular-based autonomous driving pipeline, ensuring safe, accurate, and timely awareness of human agents' possible future trajectories. The autonomous vehicle can use this information to prevent any possible accidents and create a comfortable and pleasant driving experience for the passengers and pedestrians. A wealth of research was done on the topic from the authors of robotics, computer vision, intelligent transportation systems, and other fields. However, a relatively unexplored angle is the integration of the state-of-art solutions into existing autonomous driving stacks and evaluating them in real-life conditions rather than sanitized datasets. We analyze selected publications with provided open-source solutions and provide a perspective obtained by integrating them into existing Autonomous Driving framework - Autoware Mini and performing experiments in natural urban conditions in Tartu, Estonia to determine valuability of traditional motion prediction metrics. This perspective should be valuable to any potential autonomous driving or robotics engineer looking for the real-world performance of the existing state-of-art pedestrian motion prediction problem. The code with instructions on accessing the dataset is available at https://github.com/dmytrozabolotnii/autoware_mini.

Pedestrian motion prediction evaluation for urban autonomous driving

TL;DR

This paper analyzes a set of selected methods from the literature, and presents the perspective obtained by integrating them into an existing autonomous-driving software stack - Autoware Mini - and performing experiments in natural urban conditions in Tartu, Estonia to determine the suitability of conventional motion prediction metrics.

Abstract

Pedestrian motion prediction is a key part of the modular-based autonomous driving pipeline, ensuring safe, accurate, and timely awareness of human agents' possible future trajectories. The autonomous vehicle can use this information to prevent any possible accidents and create a comfortable and pleasant driving experience for the passengers and pedestrians. A wealth of research was done on the topic from the authors of robotics, computer vision, intelligent transportation systems, and other fields. However, a relatively unexplored angle is the integration of the state-of-art solutions into existing autonomous driving stacks and evaluating them in real-life conditions rather than sanitized datasets. We analyze selected publications with provided open-source solutions and provide a perspective obtained by integrating them into existing Autonomous Driving framework - Autoware Mini and performing experiments in natural urban conditions in Tartu, Estonia to determine valuability of traditional motion prediction metrics. This perspective should be valuable to any potential autonomous driving or robotics engineer looking for the real-world performance of the existing state-of-art pedestrian motion prediction problem. The code with instructions on accessing the dataset is available at https://github.com/dmytrozabolotnii/autoware_mini.

Paper Structure

This paper contains 13 sections, 4 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Research Methods
  3. Problem Formulation
  4. Motion prediction Algorithms
  5. Experimental Setup
  6. Data collection
  7. Implementation Details
  8. Evaluation Metrics
  9. Findings
  10. Quantitative results
  11. Ablation testing
  12. A note on reproducibility of experiments
  13. Conclusion

Figures (2)

  • Figure 1: Architectural difference between implementation of state-of-art motion prediction methods and their potential implementation in a modular Autonomous Driving framework.
  • Figure 2: Data flow inside Autoware Mini framework. Detection module extracts the shapes of the objects from raw point cloud, and classifies them to pedestrian/car/other objects. Afterwards, selected prediction model outputs candidate trajectories, represented here as yellow curves