Publication Highlights
15+
Publications
500+
Citations
8
h-index
5
Top Venues
Featured Publications
Submodular Reinforcement Learning
Under Review at ICML 2024
We investigate reinforcement learning problems where the reward function exhibits submodular structure. Despite the NP-hardness of these problems, we develop practical algorithms with conditional approximation guarantees and demonstrate applications in experiment design and informative path planning.
Near-optimal multi-agent learning for safe coverage control
Advances in Neural Information Processing Systems (NeurIPS) 2022
We address the challenge of coordinating multiple agents to cover a spatial domain while maintaining safety guarantees. Our approach provides near-optimal algorithms with theoretical guarantees for safe multi-agent coverage control.
Competitive Policy Optimization
Uncertainty in Artificial Intelligence (UAI) 2021
We introduce a novel approach to multi-agent reinforcement learning through competitive optimization, with applications in autonomous racing and game-theoretic scenarios. Our method achieves superior performance in competitive environments.
Journal Publications
AMZ Driverless: The Full Autonomous Racing System
Journal of Field Robotics (JFR), 2020
📊 150+ citations | 🏆 Most cited JFR paper 2020-2021
Proof-of-concept of a Stair-climbing Add-On Device for Wheelchairs
Medical Engineering & Physics, Elsevier, 2020
📊 30+ citations | 🏥 Clinical impact
Conference Publications
Redundant Perception and State Estimation for Reliable Autonomous Racing
IEEE International Conference on Robotics and Automation (ICRA), 2019
*Equal contribution
Add-on Device to Assist in Stair Climbing of Wheelchairs
3rd Indian National Conference on Applied Mechanics (INCAM), 2017
🏆 Best Paper Award - Bio-medical Category
Preprints & Under Review
Safe Reinforcement Learning with Submodular Constraints
Submitted to ICRA 2024
🔄 Under Review
Multi-Objective Bayesian Optimization for Autonomous Systems
Submitted to AISTATS 2024
🔄 Under Review
Research Impact
🎯 Research Areas
- Reinforcement Learning
- Multi-Agent Systems
- Control Theory
- AI Safety
- Autonomous Systems
🤝 Collaborations
- ETH Zurich (Switzerland)
- Caltech (USA)
- Max Planck Institute (Germany)
- University of Oxford (UK)
- MIT (USA)
📊 Metrics
- Total Citations: 500+
- h-index: 8
- i10-index: 6
- Average citations per paper: 35
- Most cited paper: 150+ citations