This project develops PACE-Drone, an intelligent drone planning system that learns from experience rather than following pre-programmed scripts. Unlike current drones that treat each mission independently, PACE-Drone maintains a persistent belief over user preferences via Bayesian learning, actively discovers implicit constraints from historical mission logs, and balances exploration with task completion based on instruction granularity.
Honours and Masters project
Displaying 271 - 272 of 272 honours projects.
WALR — Width-Aware Language Reward for Vision-Language-Action Models
This project addresses the language ignoring problem in embodied AI, where robots learn visual shortcuts instead of following instructions. Building on our preprint establishing the relationship between planning width (instruction granularity) and learning difficulty, you will develop WALR—a reward design framework that adapts to instruction complexity. WALR scales language grounding rewards based on instruction granularity (coarse vs.