# Engineering work
Source: https://kaustubhkr.github.io/work.html

Work

# Robotics & industrial systems.

What each system does, how I built it, and the evidence behind it.

Autonomous systems

### Autonomous racing at ICRA ↗ (https://kaustubhkr.github.io/projects/autonomous-racing.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/autonomous-racing.html)

Autonomous systems / physical vehicle

### Autonomy on a physical golf cart ↗ (https://kaustubhkr.github.io/projects/golf-cart.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/golf-cart.html)

Learning & world models

### World models & policy optimisation ↗ (https://kaustubhkr.github.io/projects/reinforcement-learning.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/reinforcement-learning.html) Code ↗ (https://github.com/kaustubhkr/reinforcement-learning-toolkit)

Control engineering

### Measured C++ control ↗ (https://kaustubhkr.github.io/projects/control-runtime.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/control-runtime.html) Code ↗ (https://github.com/kaustubhkr/industrial-control-toolkit) Measurements ↗ (https://kaustubhkr.github.io/projects/control-runtime.html#evidence)

Industrial robotics

### Coordinated robot execution ↗ (https://kaustubhkr.github.io/projects/multi-robot-runtime.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/multi-robot-runtime.html)

AviRob / industrial systems

### Robot logs into traceable evidence ↗ (https://kaustubhkr.github.io/projects/machine-evidence.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/machine-evidence.html) ROSCon talk ↗ (https://www.youtube.com/watch?v=8RZy6ztm5Wg)

AviRob / geometry & verification

### Geometry-backed verification ↗ (https://kaustubhkr.github.io/projects/verification-engine.html)

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.
Technical case study ↗ (https://kaustubhkr.github.io/projects/verification-engine.html)

Other experiments: visual driving, native inference & compute ↗ (https://kaustubhkr.github.io/archive.html)

END OF SECTION 2: work.html