robotics
The Underwater Tracker Split Yaw From Translation
A target-specific depth mask and two motion models kept the vehicle's control problem small enough for real time.
Summary
A target-specific depth mask and two motion models kept the vehicle's control problem small enough for real time.
The underwater tracking system selects target depth pixels using color, disparity and temporal cues, then filters depth and image-center estimates separately. Its controller handles yaw apart from translation, avoiding a larger coupled optimization, while predictive control blends constant-velocity and stationary-target models according to recent errors. Actuation, following distance and field of view remain explicit constraints. Simulations and physical experiments beat the authors' comparison frameworks, though the abstract does not quantify that margin.
Why it matters
A target-specific depth mask and two motion models kept the vehicle's control problem small enough for real time.
Limits and context
- Its controller handles yaw apart from translation, avoiding a larger coupled optimization, while predictive control blends constant-velocity and stationary-target models according to recent errors.
- Actuation, following distance and field of view remain explicit constraints.
- Simulations and physical experiments beat the authors' comparison frameworks, though the abstract does not quantify that margin.
Key claims
A target-specific depth mask and two motion models kept the vehicle's control problem small enough for real time.
Qualification: Its controller handles yaw apart from translation, avoiding a larger coupled optimization, while predictive control blends constant-velocity and stationary-target models according to recent errors.
Evidence: source-2026-09-19-009
Sources
- arXiv preprint 2609.20731arXiv · primary research
Corrections
No corrections have been recorded for this story.