https://manvel-robotics.com/ Recent content on Manvel Avetisian — Applied Robotics Researcher Hugo -- gohugo.io en-us Tue, 14 Apr 2026 00:00:00 +0000 https://manvel-robotics.com/writing/the-elusive-art-of-the-corporate-research-lab/ Tue, 14 Apr 2026 00:00:00 +0000 https://manvel-robotics.com/writing/the-elusive-art-of-the-corporate-research-lab/ Corporate research labs sound prestigious and look fancy on paper but are often structurally broken in ways nobody talks about openly. I’ve managed multiple research teams in these settings and have seen the drama play out countless times. I want to offer a personal, insider perspective from the trenches to cover the problems — and provide some solutions. 1. Success is ill-defined Let’s start with academic research as a counterpart. Academic research has well-defined success metrics: papers, citations, replication. https://manvel-robotics.com/writing/training-and-deploying-rl-for-a-500usd-sidewalk-robot/ Tue, 31 Mar 2026 00:00:00 +0000 https://manvel-robotics.com/writing/training-and-deploying-rl-for-a-500usd-sidewalk-robot/ 1. Intro: how did the project start? I knew almost nothing about robotics, and that’s exactly why I started. After many years in AI and software engineering, I wanted to build something physical. During an interview with a self-driving car company, I was surprised to learn how much delivery robots actually cost. Impressive hardware, sensors and AI-capable SOCs pushed the price well above a couple of thousand dollars. I called BS: I was sure I could do that with cheap sensors, cheap compute, or both. https://manvel-robotics.com/sections/contact/ Mon, 01 Jan 0001 00:00:00 +0000 https://manvel-robotics.com/sections/contact/ manvel@manvel-robotics.com LinkedIn GitHub Google Scholar https://manvel-robotics.com/sections/research/ Mon, 01 Jan 0001 00:00:00 +0000 https://manvel-robotics.com/sections/research/ Experiment 01 — The Deliverator project The Deliverator project investigates using AI to compensate for cheap hardware in autonomous delivery robots. The core question: can lightweight neural networks, running on-device, achieve reliable sidewalk navigation using only basic cameras, consumer-grade IMUs, and standard GPS — bringing total build cost under $500? The entire stack is built from scratch by a single researcher: a custom Vulkan-based simulator, an RL training pipeline (SAC on JAX), vision-based navigation, teleoperation, and hardware.