Hitesh Arora

Papers

Total Citations

H-Index

About

Hitesh Arora is a researcher working at the intersection of autonomous systems, reinforcement learning, and computer vision, with a particular focus on advancing the capabilities of self-driving vehicles in complex, real-world environments. His most notable work, "Affordance-based Reinforcement Learning for Urban Driving" (2021), addresses one of the fundamental limitations of traditional autonomous vehicle pipelines — their inability to generalize effectively to unseen environments. By leveraging affordance-based representations within a reinforcement learning framework, Arora's research proposes a more adaptive and scalable approach to urban driving, moving beyond rigid modular architectures that, while interpretable, struggle with novel scenarios. This contribution has garnered 9 citations, reflecting growing interest from the autonomous driving community in end-to-end learning paradigms that balance performance with adaptability. Arora's work speaks to a broader challenge in the field: building autonomous systems that are not only capable in controlled settings but robust enough to navigate the unpredictability of real-world urban environments. His research is particularly valuable for students and practitioners exploring the frontier of intelligent transportation and embodied AI systems.