Papers
86
Total Citations
1,172
H-Index
19
About
Mohan Sridharan is a prominent researcher working at the intersection of robotics, artificial intelligence, and knowledge representation, with particular strengths in explainable AI, probabilistic planning, and autonomous systems. His most celebrated contribution, "Explainable Agency for Intelligent Autonomous Systems" (2017, 153 citations), addressed a critical challenge in modern AI: making machine learning-driven autonomous agents interpretable and trustworthy to human collaborators — a question that has only grown more urgent with AI's expanding societal role. Building on this foundation, his 2019 work on explanatory theories for human-robot collaboration further formalized how robots can communicate their reasoning and beliefs to human partners. Sridharan has also made significant advances in robot perception and planning under uncertainty. His hierarchical POMDP frameworks, including HiPPo and the vision-focused planning system from 2010, demonstrated elegant solutions for robots that must actively decide what to perceive and when. His 2015 architecture blending logical inference with probabilistic planning addressed the real-world messiness of incomplete knowledge in robotic deployment. Early contributions in mobile robot localization, obstacle detection, and real-time vision on legged platforms reflect a career-long commitment to bridging theoretical rigor with practical robotics, earning him a well-respected place in the autonomous systems research community.
Research Focus
Key Achievements
Top Papers
- 1Explainable Agency for Intelligent Autonomous Systems153 citations · 2017
- 2Practical Vision-Based Monte Carlo Localization on a Legged Robot57 citations · 2006
- 3
- 4
- 5
- 6
- 7Towards a Theory of Explanations for Human–Robot Collaboration40 citations · 2019
- 8
- 9Real-time vision on a mobile robot platform31 citations · 2005
- 10Color learning and illumination invariance on mobile robots: A survey30 citations · 2009