Selected research systems

Research systems & artifacts.

A focused selection of research projects, paper implementations, and technical systems.

SCoUT

RLC 2026 · Oral

Scalable communication for multi-agent reinforcement learning through utility-guided temporal grouping and counterfactual credit assignment.

  • Multi-agent
  • Reinforcement learning

Paper Project Code

Belief-Conditioned One-Step Diffusion

CoRL 2025 · Oral · Top 5%

Real-time trajectory planning and sensor scheduling that uses a belief-conditioned diffusion model to activate only the sensing needed.

  • Robotics
  • Generative models
  • Planning
  • Information & sensing

Paper Project Code

ComTraQ-MPC

IROS 2024 · Oral

A meta-trained DQN–MPC framework for trajectory tracking with limited active localization updates.

  • Robotics
  • Reinforcement learning
  • Planning
  • Information & sensing
  • Control & safety

Paper Code Video

Massive budgeted POMDPs

TMLR 2026

Oracle-guided meta-reinforcement learning for massive multi-component maintenance and inspection problems.

  • Planning
  • POMDPs
  • Reinforcement learning
  • Resource constraints

Paper

Risk-aware planning

Research project

Reachability-based trajectory design that balances path length and risk around obstacles.

  • Robotics
  • Planning
  • Control

Project

Deep RL for Intelligent Traffic Light Control

Technical project

Comparison of DQN and PPO policies for intelligent signal control in a SUMO-simulated traffic intersection.

  • Reinforcement learning
  • Control
  • Traffic systems

Code

Vision-based Spacecraft Trajectory Estimation Using Structure from Motion

Technical project

3D reconstruction of asteroid Bennu’s surface and spacecraft trajectory estimation using structure-from-motion techniques.

  • Computer vision
  • State estimation
  • Space systems

Code