log in  |  register  |  feedback?  |  help  |  web accessibility
PhD Defense: Towards Autonomous Driving in Dense, Heterogeneous, and Unstructured Environments
Rohan Chandra
Monday, April 18, 2022, 5:00-7:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
This dissertation addressed many key problems in autonomous driving towards handling dense, heterogeneous, and unstructured traffic environments. Autonomous vehicles (AV) at present are restricted to operating on smooth and well-marked roads, in sparse traffic, and among well-behaved drivers. We present new techniques to perceive, predict, and navigate among human drivers in traffic that is significantly denser in terms of number of traffic-agents, more heterogeneous in terms of size and dynamic constraints of traffic agents, and where many drivers may not follow the traffic rules and have varying behaviors. Our work is centered along three themes—perception, driver behavior modeling, and planning. Our novel contributions include:
  1. Improved tracking and trajectory prediction algorithms for dense and heterogeneous traffic using a combination of computer vision and deep learning techniques.
  2. A novel behavior modeling approach using graph theory for characterizing human drivers as aggressive or conservative from their trajectories.
  3. Behavior-driven planning and navigation algorithms in mixed and unstructured traffic environments using game theory and risk-aware planning.
Additionally, we have released a new traffic dataset, METEOR, which captures rare and interesting, multi-agent driving behaviors in India. These behaviors are grouped into traffic violations, atypical interactions, and  diverse scenarios. We evaluate our perception work on tracking and trajectory prediction using standard autonomous driving datasets such as the Waymo Open Motion, Argoverse, NuScenes datasets, as well as public leaderboards where our tracking approach resulted in achieving rank 1 among over a 100 methods. We apply human driver behavior modeling in planning and navigation at unsignaled intersections and highways scenarios using state-of-the-art traffic simulators and show that our approach results in fewer collisions and deadlocks compared to methods based on deep reinforcement learning.

Examining Committee:
Dean's Representative:
Dr. Dinesh Manocha    
Dr. Derek Paley   
Dr. Yiannis Aloimonos    
Dr. Pratap Tokekar    
Dr. Mac Schwager

Rohan Chandra is a fourth-year Ph.D. candidate in the GAMMA Lab at the University of Maryland, College Park advised by Prof. Dinesh Manocha. He received a master’s degree in computer science from the University of Maryland in 2018 and a bachelor's degree in electronics and communication engineering from the Delhi Technological University, India in 2016. His research focuses on autonomous driving in dense, heterogeneous, and unstructured traffic environments. He has published his work in top computer vision and robotics conferences (CVPR, ICRA, IROS) and has interned at NVIDIA in the autonomous driving team. He has served on the program committee of leading conferences in robotics, computer vision, artificial intelligence, and machine learning. He is a Fellow in the Future Faculty program organized by The Clark School, UMD and has received the UMD summer research fellowship. He has given invited talks at academic seminars and workshops and has served on a robotics panel at RSS’21 alongside distinguished faculty. Outside of research, he enjoys teaching and mentoring younger students through diversity and inclusion initiatives like AI4ALL.

This talk is organized by Tom Hurst