Autonomous Delivery Robotics
Multi-phase autonomous-delivery robotics work integrating ROS 2 navigation, robot perception, localization, manipulation and environment interaction.
- Nav2
- AMCL
- YOLO
- MoveIt 2
- ResNet18
01
What it does
Multi-phase autonomous-delivery robotics work integrating ROS 2 navigation, robot perception, localization, manipulation and environment interaction.
The completed work spans single-floor autonomous navigation, package identification and localization, robotic pick-and-place, elevator perception and interaction, semantic indoor localization and language-conditioned visual grounding.
An integrated robotics programme demonstrated through validated modules — not a single production system.
02
Selected modules
Autonomous Navigation
Nav2 and AMCL-based room-to-room navigation within a structured residential environment.
Package Perception
OCR-based label reading, YOLO-based package awareness and ArUco pose estimation for manipulation.
Manipulation
OpenManipulator and MoveIt 2 integration for simulated package interaction.
Elevator Perception
YOLO-based elevator door-state detection combined with temporal decision logic for safer elevator-entry triggering.
Button Interaction
Elevator button detection and classification connected to inverse-kinematics-based manipulator targeting.
Semantic Localization
ResNet18-based classification of indoor locations using real building footage.
OCR Label Reading
Simulated address-label recognition publishing the detected label “Apt 48”.
DQN Dynamic-Obstacle Navigation
A DQN policy uses 24 forward LiDAR rays and a relative-goal vector to reach the target while avoiding moving obstacles in a custom Gymnasium/Pygame simulation. 82% success across 100 zero-exploration evaluation episodes in the 20-moving-obstacle stress test.
03
Results
- 100%
- Elevator entry trigger success
- 0
- False-positive entry triggers
- 0.778
- Semantic localization test accuracy
Tested simulation conditions
Tested simulation conditions
04
Further integration
Later work toward ROS 2 grounded-task bridging, action-level safety gating, mission execution and DRL/Nav2 supervision remained follow-on integration rather than completed end-to-end functionality.
05
Technology
- ROS 2
- Nav2
- AMCL
- YOLO
- OCR
- ArUco
- OpenManipulator
- MoveIt 2
- ResNet18
Next project
05 — Vision-Language Model Evaluation Pipeline