Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting

01/07/2021
by   Katie Luo, et al.
19

In this paper, we address the important problem in self-driving of forecasting multi-pedestrian motion and their shared scene occupancy map, critical for safe navigation. Our contributions are two-fold. First, we advocate for predicting both the individual motions as well as the scene occupancy map in order to effectively deal with missing detections caused by postprocessing, e.g., confidence thresholding and non-maximum suppression. Second, we propose a Scene-Actor Graph Neural Network (SA-GNN) which preserves the relative spatial information of pedestrians via 2D convolution, and captures the interactions among pedestrians within the same scene, including those that have not been detected, via message passing. On two large-scale real-world datasets, nuScenes and ATG4D, we showcase that our scene-occupancy predictions are more accurate and better calibrated than those from state-of-the-art motion forecasting methods, while also matching their performance in pedestrian motion forecasting metrics.

READ FULL TEXT

page 6

page 13

page 14

research
03/04/2022

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

Forecasting pedestrians' future motions is essential for autonomous driv...
research
01/17/2021

LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting

Forecasting the future behaviors of dynamic actors is an important task ...
research
06/26/2023

SIMF: Semantics-aware Interactive Motion Forecasting for Autonomous Driving

Autonomous vehicles require motion forecasting of their surrounding mult...
research
08/11/2023

A Game-Theoretic Framework for Joint Forecasting and Planning

Planning safe robot motions in the presence of humans requires reliable ...
research
10/18/2019

Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data

In this paper, we tackle the problem of relational behavior forecasting ...
research
03/14/2020

Collaborative Motion Prediction via Neural Motion Message Passing

Motion prediction is essential and challenging for autonomous vehicles a...
research
04/14/2022

Joint Forecasting of Panoptic Segmentations with Difference Attention

Forecasting of a representation is important for safe and effective auto...

Please sign up or login with your details

Forgot password? Click here to reset