GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation

By Thomas Gilles, Stefano Sabatini, Dzmitry V. Tsishkou, Bogdan Stanciulescu, Fabien Moutarde. IEEE International Conference on Robotics and Automation, 2021

308 citations recorded by the source corpus.

In this paper, we propose GOHOME, a method leveraging graph representations of the High Definition Map and sparse projections to generate a heatmap output representing the future position probability distribution for a given agent in a traffic scene. This heatmap output yields an unconstrained 2D grid representation of agent future possible locations, allowing inherent multimodality and a measure of the uncertainty of the prediction. Our graph-oriented model avoids the high computation burden of representing the surrounding context as squared images and processing it with classical CNNs, but focuses instead only on the most probable lanes where the agent could end up in the immediate future. GOHOME reaches 2nd on Argoverse Motion Forecasting Benchmark on the Misskate6metric while achieving significant speed-up and memory burden diminution compared to Argoverse 1st place method HOME. We also highlight that heatmap output enables multimodal ensembling and improve 1st place MissRate6by more than 15% with our best ensemble on Argoverse. Finally, we evaluate and reach state-of-the-art performance on the other trajectory prediction datasets nuScenes and Interaction, demonstrating the generalizability of our method.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dbe41b7715078917c2f65dfda316c34d47afe697

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dengxin Dai
2. Nigamaa Nayakanti
3. Ahmed S. Hefny
4. Shaoshuai Shi
5. Khaled S. Refaat
6. Li Jiang
7. Balakrishnan Varadarajan
8. Bernt Schiele

In Automotive Engineering

1. Shaoshuai Shi
2. Bernt Schiele
3. Dengxin Dai
4. Li Jiang
5. Nigamaa Nayakanti
6. Khaled S. Refaat
7. Benjamin Sapp

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dengxin Dai
3. Xiaogang Wang
4. Bernt Schiele
5. Ming-Hsuan Yang
6. Shaoshuai Shi
7. Trevor Darrell
8. Alan L. Yuille

Citations in the corpus

• MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction (2021, methodology): “It is interesting to relate this criteria to the ensembling and sampling method employed by GOHOME [21].”
• Motion Transformer with Global Intention Localization and Local Movement Refinement (2022, methodology): “HOME series [18, 17] generate trajectories with sampling on a predicted heatmap.”