Multimodal Motion Prediction Based on Adaptive and Swarm Sampling Loss Functions for Reactive Mobile Robots
Paper in proceeding, 2022

Making accurate predictions about the dynamic environment is crucial for the trajectory planning of mobile robots. Predictions are by nature uncertain, and for motion prediction multiple futures are possible for the same historic behavior. In this work, the objective is to predict possible future positions of the target object for the collision avoidance purpose for mobile robots by considering different uncertainty by combining a sampling-based idea with data-driven methods. More specifically, we propose a major improvement on a loss function for multiple hypotheses and test it with convolutional neural networks on motion prediction problems. We implement post-processing heuristics that produce multiple Gaussian distribution estimations, and show that the result is suitable for trajectory planning for mobile robots. The method is also evaluated with the Stanford Drone Dataset.

Multimodal motion prediction

Author

Ze Zhang

Chalmers, Electrical Engineering, Systems and control

Emmanuel Dean

Chalmers, Electrical Engineering, Systems and control

Yiannis Karayiannidis

Chalmers, Electrical Engineering, Systems and control

Knut Åkesson

Chalmers, Electrical Engineering, Systems and control

IEEE International Conference on Automation Science and Engineering

21618070 (ISSN) 21618089 (eISSN)

Vol. 2022-August 1110-1115
978-1-6654-9042-9 (ISBN)

18th IEEE International Conference on Automation Science and Engineering, CASE 2022
Mexico city, Mexico,

Project ViMCoR

Volvo Group (ProjectViMCoR), 2019-09-01 -- 2021-08-31.

Infrastructure

C3SE (Chalmers Centre for Computational Science and Engineering)

Subject Categories

Robotics

Computer Vision and Robotics (Autonomous Systems)

DOI

10.1109/CASE49997.2022.9926544

Related datasets

Stanford Drone Dataset [dataset]

URI: https://cvgl.stanford.edu/projects/uav_data/

More information

Latest update

10/27/2023