Overview Pipeline Algorithms Benchmark Results
BEng Final Year Project · 2026

ROS2 Path
Planning on
UR3e

University of Portsmouth

Implementing and benchmarking the RRT family of path-planning algorithms on a Universal Robots UR3e collaborative arm using ROS2 Jazzy and MoveIt2.

3
Algorithms
4
Scenarios
6
DOF
10×
Memory Saved
UR3e collaborative robot schematic
01 — Project Overview

What This Project Does

Collaborative robotic arms must navigate complex 3D joint spaces to reach target configurations without collisions. This project establishes a complete ROS2-to-hardware pipeline for a UR3e manipulator, then implements and benchmarks three generations of sampling-based path planners.

The focus is on RRT*FN — a Fixed-Node variant that achieves near-optimal path quality while capping memory usage. On a robot that plans thousands of paths over its operational lifetime, bounded memory is not optional.

Hardware
UR3e
DOF
6-Axis
Payload
3 kg
Reach
500 mm
OS
Ubuntu 24.04
ROS
Jazzy
Planner
MoveIt2
Supervisor
Dr. Sotirios S.
02 — Hardware Pipeline

Signal Path to Steel

// UI
RViz
// PLAN
MoveIt2
// CTRL
JTC
// DRV
ur_robot_driver
// HW
UR3e
Network

USB-to-Ethernet adapter with static IP. URCap External Control plugin synchronised to host IP.

Execution

Planned trajectories dispatched via joint_trajectory_controller and executed on real hardware.

Validation

Full pipeline validated on physical UR3e. Simulation parity confirmed in Gazebo beforehand.

03 — Algorithm Family

Three Generations of RRT

RRT

Rapidly-exploring Random Tree. Samples the configuration space and grows a tree toward each sample. Fast but sub-optimal — it takes the first path it finds and stops.

Fastest
Characteristic
∞ memory · sub-optimal · no rewiring
RRT*

Adds a rewiring step that continuously improves path quality. Provably asymptotically optimal — but the tree grows without limit, consuming unbounded memory.

Optimal Paths
Characteristic
∞ memory · near-optimal · rewiring
◈ This project's focus
RRT*FN

Fixed-Node variant. Caps the tree at a maximum node count by evicting the least useful nodes. Near-optimal quality with bounded, predictable memory usage.

Best of Both
Characteristic
Bounded memory · near-optimal · rewiring
04 — Performance Benchmark

Algorithm Showdown

05 — Results & Conclusions

What We Found

10×
Memory reduction vs RRT*
<2%
Path quality loss
4
Validated scenarios
100%
Pipeline on real hardware

Hardware Pipeline

The ROS2 / MoveIt2 system was successfully configured and the UR3e was controlled via planned trajectories from RViz. The full communication pipeline was validated on real hardware — not just simulation — including live trajectory execution.

Algorithm Outcome

RRT*FN maintains bounded memory while producing near-optimal paths comparable to RRT*. RRT was fastest but least optimal. This demonstrates a complete open-source pipeline for further advanced path planning research.

06 — Tech Stack

Tools of the Trade

ROS2 Jazzy
MoveIt2
RViz
ur_robot_driver
Ubuntu 24.04
Gazebo
C++ / Python
OMPL
UR3e 6-DOF
USB-to-Ethernet
joint_trajectory_controller
URCap External Control