Lomash Relia

M.Tech student and robotics researcher specializing in autonomous systems, space robotics, computer vision, deep learning, and edge AI.

How I Build Autonomous Systems

I approach robotics as a systems engineering problem - not just a machine learning problem.

For a robotic system to operate reliably, perception, control, computation, and hardware constraints must be designed together. I focus on building pipelines that remain stable and predictable when exposed to real-world latency, power limits, and sensor uncertainty.

My Engineering Approach

1. Start from the Control Objective
Define what stability, convergence, or performance actually means in measurable terms.

2. Validate in Simulation
Model kinematics, camera geometry, and control laws under controlled conditions.

3. Deploy Under Constraints
Move to hardware and test under realistic power, thermal, and computation limits.

4. Measure Everything
Latency, convergence time, failure modes, and repeatability matter more than isolated demos.

What I Value

  • Mathematical grounding behind algorithms
  • Clear system architecture
  • Stability over novelty
  • Deployment over demonstration

I am particularly motivated by problems in space robotics, physical AI, and perception-driven control systems where reliability is non-negotiable.