Oswin So
Scholar

Oswin So

Google Scholar ID: AwlxGQgAAAAJ
Massachusetts Institute of Technology
SafetyStochastic Optimal ControlReachabilityReach AvoidDynamic Games
Citations & Impact
All-time
Citations
435
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
9
list available
Resume (English only)
Academic Achievements
  • Paper 'Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL' accepted to RSS 2025
  • Paper 'DGPPO: Learning and Using Discrete Graph CBFs for Safe MARL' accepted to ICLR 2025
  • Paper 'GCBF+: Constructing Control Barrier Functions with Theoretical Safety Guarantees for Arbitrary Swarms' accepted to IEEE Transactions on Robotics (T-RO), 2024
  • Paper 'Solving Optimal Control Problems with Reach-Avoid Constraints Using Deep RL' accepted to NeurIPS 2024
  • Paper 'Combining Deep RL and Optimal Control to Synthesize Safe, Stabilizing Controllers' accepted to RSS 2023