Socially Compliant Multi-Agent Planning and Navigation in Challenging Environments
University of Texas, Austin
Multi-agent social navigation is a complex problem in unstructured and challenging environments due to a myriad of factors such as limited observability, rough terrains, unpredictable non-cooperative agents, and so on. Research in multi-agent planning and navigation is spread across various domains such as perception, prediction, modeling, simulation, and planning in order to make multi-robot planning in such environments safer, efficient, and socially compliant in the presence of humans. In this talk, I will present a new framework for modeling socially compliant multi-agent planning and navigation in challenging environments. I will present results from experiments in autonomous driving and indoor social navigation that employ this framework. I will conclude by outlining a research vision that highlights open questions, presents opportunities for future work, and promotes diversity and inclusion, in this exciting and rapidly evolving field.
Rohan Chandra is currently a postdoctoral research fellow in Texas Robotics, advised by Dr. Joydeep Biswas and Dr. Peter Stone, at the University of Texas, Austin. Rohan obtained his B.Tech from the Delhi Technological University, New Delhi in 2016 and completed his MS and PhD in 2018 and 2022 from the University of Maryland advised by Dr. Dinesh Manocha. His doctoral thesis focused on autonomous driving in dense, heterogeneous, and unstructured traffic environments. Rohan is a Microsoft Future Leader in Robotics and AI, KAUST Rising Star in AI 2023, UMD’21 Future Faculty Fellow, RSS’22 Pioneer, and he is a recipient of the UMD’20 summer research fellowship. He has published his work in top computer vision and robotics conferences (CVPR, ICRA, IROS) and has participated in workshops and program committees of leading conferences in robotics, computer vision, artificial intelligence, and machine learning. He has also given invited talks at academic seminars and workshops and has served on robotics panels alongside distinguished faculty. Webpage:http://rohanchandra30.github.io/.
About the Seminar Series
The Future Leaders in Robotics and AI: Celebrating Diversity and Innovation Seminar Series is part of the University of Maryland and Microsoft Robotics and Diversity Initiative. This is a nationwide online seminar series for PhD students, postdoctoral researchers, or early-career professionals, especially underrepresented minorities and women. The seminar series highlights the latest research and innovation in the field of robotics and AI. The series is intended to provide exposure and mentorship opportunities to the speakers, build a network of innovators across the country, and support the speakers’ career planning.
The seminars are held once per month during the academic year. There are two speakers per seminar. Each speaker gives a 20-minute research presentation followed by a Q&A segment. Immediately after the second seminar, the speakers participate in a discussion with faculty.