I-Corps: Translation Potential of Safety-Critical Embedded Motion Control for Human-Interactive Mobility Systems

This I-Corps project is based on the development of a motion-control platform for safe, remote-free operation of electric mobility robotic systems. Many current systems depend on handheld remotes, open-loop commands, and reactive safety features, creating usability and safety concerns when users, terrain, or operating conditions change unexpectedly. This technology combines onboard sensing, embedded intelligence, and real-time control to infer user intent, adapt to uncertainty, and enforce limits on speed, acceleration, braking, location, and operating modes. The technology has been validated with an electric skateboard while the underlying technology may support a broader range of micromobility, assistive mobility, personal transportation, and interactive robotic products. This technology may make advanced motion control more intuitive and dependable on affordable embedded hardware, and may reduce barriers to adoption, improve user confidence, and enable manufacturers to differentiate products through safety and intelligent interaction. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of a safety-critical edge-intelligence and embedded motion-control platform for human-interactive systems operating under uncertainty. Current motion controllers primarily execute user commands and rely on heuristic protections. This technology integrates learning-enabled disturbance estimation, robust control barrier functions, onboard rider-intent inference, and deterministic field programmable gate array (FPGA)-based implementation. Disturbance estimation identifies unmodeled forces, user variability, terrain effects, and motor-response uncertainty in real time. Robust control barrier functions then use this information to enforce mathematically defined safety constraints, including bounded speed and acceleration, safe braking, geofencing, and safe transitions among operating modes. This technology combines uncertainty awareness, formal safety enforcement, and predictable low-latency computation within an embedded platform. Users may benefit from more natural interaction, fewer communication-related failure modes, and stronger protection against changing operating conditions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.