Rhys Howard
Papers
3
Total Citations
11
H-Index
2
About
Rhys Howard is a robotics researcher whose work focuses on enabling autonomous systems to perceive, reason, and act reliably in complex, dynamic, and open-ended environments. His research spans three key areas: causal discovery for behavior modeling, real-time deformable object tracking, and competency-aware perception. In his most-cited work (2023, 5 citations), Howard developed temporal observation-based causal discovery techniques to help autonomous robots reason about the behavior of dynamic agents—such as human drivers—by inferring causal relationships from observational data alone. This work is critical for safe navigation in unpredictable settings. He also introduced a novel slicing method for tracking linear deformable objects (2021, 4 citations), enabling efficient, real-time tracking of cables, ropes, or hoses by recursively partitioning point clouds. Additionally, Howard’s work on competency-aware object detection (2021, 2 citations) addresses a major limitation of deep learning: the inability to recognize when a model is operating outside its training distribution. By evaluating novelty in open-ended environments, his approach allows robots to “know when they don’t know,” a vital step toward trustworthy autonomy. Howard’s contributions are foundational for building robots that are not only capable but also cautious and context-aware.
Research Focus
Key Achievements
Top Papers
- 1
- 2Tracking linear deformable objects using slicing method4 citations · 2021
- 3