Figure from Multimodal trajectory prediction via topological invariance for navigation at uncontrolled intersections

CoRL '20

Multimodal trajectory prediction via topological invariance for navigation at uncontrolled intersections

Junha Roh, Christoforos Mavrogiannis, Rishabh Madan, Dieter Fox, Siddhartha Srinivasa

Conference on Robot Learning (CoRL), 2020

PDFVideoCodeBibTeX

We abstract traffic at intersections into a set of modes using a notion of topological invariance, and construct a Graph Neural Network based model (MTP) that conditions multiagent trajectory prediction on the likelihood of modes given observation of past behavior. MTP empowers a MPC to safely traverse uncontrolled intersections across a variety of challenging intersection scenarios on the CARLA simulator.

BibTeX

@inproceedings{roh2020invariance,
  title  = {Multimodal trajectory prediction via topological invariance for navigation at uncontrolled intersections},
  author = {Junha Roh and Christoforos Mavrogiannis and Rishabh Madan and Dieter Fox and Siddhartha Srinivasa},
  booktitle = {Conference on Robot Learning (CoRL)},
  year   = {2020}
}

Lab members

All publications