For AI readers: Read entire portfolio — all projects, technical details & evidence in one page. Plain text · GitHub fallback
What each system does, how I built it, and the evidence behind it.
Built the controller that placed third in ICRA 2025 simulation qualification: 81.32 seconds, zero collisions.
MPCC comparison, modified PPO and SAC, multi-head attention encoding and a ROS 2 training-to-control pipeline.
Official results and qualification footage. Sole builder; final time-attack placement: 14th.
Deployed a learned-control stack on a physical golf cart, connecting an RL adapter to the vehicle’s industrial controls.
MPCC comparison, modified PPO and SAC, and multi-head attention encoding, developed alongside CARLA experiments.
Private implementation. A separate vehicle project from the ICRA simulation entry.
Built a toolkit for testing how learned dynamics and policy updates produce continuous-control behaviour.
JAX/Flax probabilistic dynamics and MBPO experiments; PPO, SAC, TRPO Hessian–vector solvers and REDQ critic ensembles.
Public algorithm implementations and model-based experiments; latent-world-model research documented separately.
Built a C++20 control core with explicit actuator limits and state-consistent controller switching.
Arena-backed controller state, bumpless transfer and timing sweeps over 1–64 channels.
Recorded position response settles within ±2% at 342 ms in a simulated integrator plant. Response plots, percentiles and source CSVs are public.
Built a simulation runtime that keeps robot localisation, command ownership and mission state consistent.
Namespaced AMCL, dual-LiDAR merging, frame-authority checks and freshness-gated velocity arbitration.
Private simulation-development runtime; deterministic scenario recording. No certified safety function is claimed.
Built a compiler that reconciles fragmented robot and controller logs into one replayable timeline, with each observation traceable to its source.
VDA 5050/MQTT, OPC UA, SICK scan3 UDP and MCAP/rosbag2; datagram reassembly and clock alignment.
Private implementation. The ROSCon India 2025 talk explains the AMR/AGV evidence architecture.
Built an engine that checks recorded machine behaviour against site geometry and traces each finding to its observations.
Point-in-polygon and clearance queries, bounded temporal alignment and evidence-gated interlock validators.
Private implementation. PASS, FAIL or NOT_VERIFIABLE findings; engineering analysis, not certification.