Leo Rover: Autonomous Mobile Robot

A physical Leo Rover built up and deployed by a five-person team: SLAM, path planning and real-time obstacle detection with ROS 2, tested in the lab arena.

Robotics
# overview

Problem to result

Who had the problem, what I built, the hardest part, and what it achieved.

01 · The problem

A five-person team had to get a Leo Rover to explore an unknown arena on its own, find coloured cubes and pick them up in a single 20-minute mission, where one failure (a blocked sensor, a dropped link, a missed grasp) ended the run.

02 · What I built

A rover that maps an unknown arena, spots coloured cubes with its camera and picks them up with its arm, with no one driving it.

03 · The hardest part, and how I solved it

Fitting an arm, gripper, onboard computer, camera and electronics on a small rover without blocking the LiDAR's 360° view or making it tip over. I designed an elevated two-plate sled that sits 4 mm above the LiDAR, mounted the arm front-centre and made the computer plate movable to balance the weight, then split power into two battery domains so the arm's current spikes couldn't destabilise the computer.

04 · The results

Navigation accuracy of 95%; a stability factor of 1.71 with the arm stowed and 1.58 extended; mounts with a safety factor of 2.248 at 1.5× load; about 1.4 h of battery against a 20-minute mission.

# features

Key Features

Interactive 3D structural breakdown of the LEO Rover.

LOADING ASSETS
0%

SLAM

Simultaneous Localisation and Mapping utilising 2D/3D LiDAR fusion to construct high-fidelity spatial maps of unknown environments in real-time.

Autonomous Navigation

Dynamic path planning and robust obstacle avoidance algorithms ensuring seamless point-to-point traversal across complex terrain.

Computer Vision

Edge-deployed YOLOv8 inference enabling rapid object detection, semantic segmentation, and advanced environmental perception.

ROS2 Architecture

A decentralised, highly modular communication framework managing sensor data streams and autonomous state machines continuously.

Path Logging

Comprehensive telemetry recording system tracking odometry, executed paths, and obstacle metadata for post-mission kinematic analysis.

# products

Product Showcase

Deep dive into the specialized hardware components used in our mobile autonomous systems.

RPLidar Sensor
Active

Hardware Module

RPLidar Sensor

A high-performance 360-degree laser range scanner. Provides the robot with precise spatial awareness and real-time mapping capabilities.

Precision
92%
Range
85%
# files

Design Files & CAD

Models, schematics, and assets.

Autonomous Mobile Robot Assembly

# simulation

Live Simulation Output

Simulated console execution.

simulation
$_▋
# videos

Project Walkthroughs

Click any video to play.

Perception System (Rover's PoV)
Live

Perception System (Rover's PoV)

Object detection and LIDAR perception capabilities from the Rover's point of view.

Arm Movement Testing
3:48

Arm Movement Testing

Testing the movement of the arm.

Structural Construction
5:20

Structural Construction

The construction of the robot.

Trail Run
7:15

Trail Run

First run of the robot in a trail environment.

Navigation Simulation
1:45

Navigation Simulation

Autonomous Mobile Robot navigation simulation in a controlled environment.

Autonomous Navigation
2:15

Autonomous Navigation

Autonomous Mobile Robot navigation simulation - Alternative scenario.

Navigation toward to block
1:20

Navigation toward to block

Autonomous Mobile Robot navigation toward a specific block.

Return to intial position after mission (Simulation Demo)
Live

Return to intial position after mission (Simulation Demo)

Simulation of the robot's navigation path.

Arm Manipulation (Simulation)
Live

Arm Manipulation (Simulation)

Simulation of the robot's arm manipulation.

Emergency brake (Simulation)
Live

Emergency brake (Simulation)

Demonstration of the robot's safety features and protocols.

Final Evaluation
Live

Final Evaluation

Testing the integrated SLAM, path planning, and YOLOv8 object detection systems during an autonomous run.

# challenges

Problems & Fixes

What went wrong while building it, and how each problem was solved.

Mechanical01 / 26

Five parts (arm, gripper, NUC, camera, electronics) all needed space, and a flat layout put them in the LiDAR's scan plane, blocking much of its 360° view and degrading SLAM

How it was fixed

Built an elevated sled. The M5 × 50 mm spacers put the upper plates 4 mm above the LiDAR's top (41 mm LiDAR + 5 mm mount = 46 mm), so the 360° view stays clear

# repositories

Get code

GitHub repositories for this project.

Leo Rover: Autonomous Mobile Robot Repository

Access the complete source code on GitHub.

Quick Start
$ git clone https://github.com/prathapselvakumar/Autonomous-Mobile-Robot-LEO-Rover.git
$ cd Autonomous-Mobile-Robot-LEO-Rover
$ pip install -r requirements.txt
$ python3 src/main.py
# recognition

Noticed by RealSense

This project caught the attention of RealSense's VP of Developer Ecosystem.

Noticed byChris MatthieuVP, Developer Ecosystem · RealSense
“Awesome! Great job Sarath Kumar Senthilkumar Kavitha and thanks for using RealSense!!”

Posted on teammate Sarath Kumar's write-up of the project. RealSense is the depth-camera platform behind the rover's perception pipeline (colour, shape and depth detection).

View the post on LinkedIn

Team

The dedicated team of engineers and innovators behind the Autonomous Robot project.

Prathap Selvakumar
Ruiyang
Joao Lopes
Jiaxin Tang
Sarath Kumar
Prathap Selvakumar

Computer Vision and Navigation

Joao Lopes

Design, 3D printing and hand‑eye calibration

Sarath Kumar

Navigation and SLAM

Ruiyang

Navigation and spatial awareness

Jiaxin Tang

SLAM and spatial awareness