SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies.
Matt VitelliYan ChangYawei YeMaciej WolczykBlazej OsinskiMoritz NiendorfHugo GrimmettQiangui HuangAshesh JainPeter OndruskaPublished in: CoRR (2021)
Keyphrases
- real world
- macro actions
- driving simulator
- synthetic data
- data mining
- dangerous situations
- driver assistance systems
- vehicle detection
- heuristic search
- wide range
- real time
- data sets
- traffic accidents
- planning problems
- case study
- stochastic domains
- road traffic
- partially observable markov decision processes
- predictive state representations
- car navigation
- markov decision problems
- moving vehicles
- ai planning
- production planning
- decision theoretic
- travel time
- domain independent
- decision support
- image sequences