TrustMHE monitors AI prediction errors online and blends AI-based planning costs with a constant-velocity fallback, significantly reducing crashes in closed-loop simulation.
BEVFormer: Learning Bird’s-Eye-View Representation from Multi- camera Images via Spatiotemporal Transformers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing System Self-Awareness and Trust of AI: A Case Study in Trajectory Prediction and Planning
TrustMHE monitors AI prediction errors online and blends AI-based planning costs with a constant-velocity fallback, significantly reducing crashes in closed-loop simulation.