Sfoglia categorie
Esplora
Fiverr Pro
Italiano
$
USD
Aman Patel
@amanpatel720
Robotics Expert
India
Inglese, Hindi, Marathi, Gujarati
Chi sono
Robotics Engineer specializing in ROS2, high-fidelity simulation, & RL control. I help startups & labs build digital twins & deploy autonomous systems.
Key Expertise:
- Navigation: SLAM Toolbox & Nav2 (AMR navigation).
- Manipulation: MoveIt2 path planning, kinematic solvers (UR5, KUKA).
- AI & Simulation: NVIDIA Isaac Sim, Isaac Lab, Gazebo Sim, PyTorch PPO.
- Integration: Dockerized containers for zero-setup execution.
I deliver production-grade C++/Python code ready for physical hardware. Let's build reliable systems, first time.
Competenze
Aman Patel
offline •
Tempo di risposta medio: 2 ore
Consulta i miei servizi
Automazioni industriali
I will simulate and program robotic arms in ros2 with moveit2 and gazebo
App desktop
I will program robotic arm manipulation and moveit in ros2
Portfolio
Esperienza lavorativa
Robotics Simulation & Control Engineer
Freelancer.com • Lavoratore autonomo
Jan 2024 - Present • 2 yrs 7 mos
Provide direct R&D simulation and control design services for robotics startups, industrial automation integrators, and research labs. Key Focus Areas & Tech Stack: - Simulation Platforms: NVIDIA Isaac Sim, Isaac Lab (Gym), MuJoCo, Webots. - Control & AI: Reinforcement Learning (PPO, SAC via Stable-Baselines3), MPC, Whole-Body Control (WBC). - Hardware & Bridging: ROS 2 (Humble/Jazzy), C++, Python, Unitree SDK2 low-level torque control. Key Achievements: - Designed and validated Sim-to-Real (Sim2Real) reinforcement learning locomotion pipelines for quadrupeds, achieving 98%+ success rates on physical platforms (Unitree Go2/B2). - Rigged and calibrated over 15 custom CAD assemblies into physics-accurate USD and MJCF robot models, correcting mass properties, inertia tensors, and joint friction limits. - Built digital twin environments for warehouse conveyor cells and AMR fleets, validating throughput metrics and eliminating layout configuration conflicts prior to physical deployment. - Deployed Omniverse Replicator synthetic data pipelines, generating 10K+ automatically labeled training images to train computer vision models with high mAP accuracy.
