Reachability-Based Geometric Simplification

Reachability-Based Geometric Simplification

Real-time obstacle avoidance is a cornerstone of safe robotic manipulation in dynamic or unstructured environments. To maintain safety protocols, robot controllers must perform precise estimation of the minimal distance between robot links and environmental objects.

You will develop a novel method to identify and model the "externally reachable" surfaces of complex, non-watertight meshes. The core idea is to determine which parts of a mesh can be contacted by obstacles of a specific resolution, effectively filtering out internal or shielded geometry.

This work is inspired by the Alpha Wrap [1] algorithm but aims to extend its current implementation to better serve the needs of robotic distance estimation. The resulting "reachability-aware" geometry will serve as the optimized input for subsequent convex decomposition.

How we work together

We believe that we are better together than apart. For our office-based teams, this means working in-person at least 3 days per week. Onsite roles require full-time presence in the company’s facilities. Field roles are most effectively done outside of the company’s main facilities, generally at the customers’ or suppliers’ locations.

About Philips

We are a health technology company.