Adaptive Control TRIZ Cases
- Closed-Course Scenario Replay for Rare AV Training Cases
Rare real-world driving events are recreated on a closed course so AVs can collect repeatable training data and improve edge-case responses.
- Autonomous Vehicle Motion Planning With Shared-Backbone Trajectory Ranking
A two-stage shared-backbone planner generates high-recall trajectories and ranks them with full scene context to cut latency and energy use.
- Relative Position-Aware Attention With Fast-Memory Tiling
Fast-memory tiling and precomputed relative embeddings cut transformer attention latency for more accurate object and trajectory prediction.
- Distributed Chassis Control for Coupled Autonomous Vehicle Subsystems
Multi-agent Co-DMPC coordinates steering, braking, and suspension to handle strong coupling with lower computational burden.