Ball-Picking Robot
A robot built in a 10-day competition that autonomously detects, picks up, aims, and throws colored balls. Our team finished second overall.
NTUT PBL, representing HCMUT
Goal, approach and outcome
- Goal
- Autonomously detect, pick, aim, and throw colored balls under competition rules and a hard time limit.
- Approach
- OpenCV for robust ball detection, embedded C for trajectories and actuation, and fast on-site integration across a 10-student team.
- Outcome
- Second place overall at NTUT PBL 2023, with press coverage in Taipei Tech Post.
Building and testing
- OpenCV vision pipeline to detect red balls and reject distractors (selection improved vs early prototypes)
- Embedded C control stack for target recognition, throw trajectories, and pick-and-throw actuation
- Integration and on-site testing across a 10-student team
On-site testing of the pick sequence before scoring runs.
Aim-and-throw cycle under competition conditions.
The robot as competitors and judges would see it.
How it played
Detect
Find the right colored balls.
Pick
Grab a target from the field.
Aim
Line up the throw.
Throw
Release toward the goal.
Workshop clip from the NTUT PBL program.
Result: second place
Represented Ho Chi Minh City University of Technology (HCMUT) at the Project-Based Learning program hosted by National Taipei University of Technology (NTUT). In a 10-day sprint, our team built an autonomous ball-picking robot and placed second overall.
Sources: YouTube workshop clip and Taipei Tech Post Issue 61.
