Encoder-Orientation Sensor Fusion for Ground Robot Navigation

projects

This project focused on developing the core sensing, control, and navigation components for an autonomous ground robot, including:

  • Low-level control: Developed an encoder-based motor controller using a Raspberry Pi Pico and MicroPython.
  • Localization: Fused wheel encoder and orientation sensor data to estimate the robot's motion and orientation.
  • Obstacle avoidance: Developed a velocity controller using LiDAR data and deployed it on an NVIDIA Jetson Orin Nano for autonomous obstacle avoidance.
Autonomous ground robot navigation
Figure 1: Autonomous ground robot navigation and obstacle avoidance
TurtleBot obstacle avoidance
Figure 2: Obstacle avoidance with TurtleBot

The system was developed as a prototype for autonomous vineyard data collection. The LiDAR-based velocity controller was additionally evaluated on a TurtleBot to validate its obstacle avoidance performance.

Dimple Bhuta
Authors
Robotics Engineer & Researcher
Robotics engineer and researcher with 10+ years of experience specializing in robotics and computer vision.