Importance is in your attention: agent importance prediction for autonomous driving

no code implementations • 19 Apr 2022 • Christopher Hazard, Akshay Bhagat, Balarama Raju Buddharaju, Zhongtao Liu, Yunming Shao, Lu Lu, Sammy Omari, Henggang Cui

Trajectory prediction is an important task in autonomous driving.

Autonomous Driving Trajectory Prediction

How to Backpropagate through Hungarian in Your DETR?

no code implementations • 12 Nov 2022 • Lingji Chen, Alok Sharma, Chinmay Shirore, Chengjie Zhang, Balarama Raju Buddharaju

The DEtection TRansformer (DETR) approach, which uses a transformer encoder-decoder architecture and a set-based global loss, has become a building block in many transformer based applications.

PBP: Path-based Trajectory Prediction for Autonomous Driving

no code implementations • 7 Sep 2023 • Sepideh Afshar, Nachiket Deo, Akshay Bhagat, Titas Chakraborty, Yunming Shao, Balarama Raju Buddharaju, Adwait Deshpande, Henggang Cui

Goal-based prediction models simplify multimodal prediction by first predicting 2D goal locations of agents and then predicting trajectories conditioned on each goal.

Autonomous Driving Inductive Bias +1