HAZARD DETECTION AI SYSTEM FOR AUTONOMOUS VEHICLE
Lead Research Organisation:
Brunel University London
Department Name: Electronic and Computer Engineering
Abstract
Perform literature review.
Develop a Perception AI system based on deep learning using publicly available data (e.g. KAIST Multi-Spectral Day/Night Data Set (Choi et al., 2018)) to: (a) Predict the intent for different road users e.g. pedestrians, cyclists etc. (b) Detect static road features e.g. road works, road signs etc. and (c) Detect weather condition e.g. fog, rain etc.
Investigate the deep learning framework e.g. TensorFlow or PyTorch.
Build, train, test and validate the neural network.
Determine the performance of the AI in an unconstrained environment.
Investigate reinforcement learning for continuous learning of the developed AI system.
Develop a Hazard Detection AI system for AV using deep learning based on the output from the Perception AI system.
Build, train, test and validate the neural network.
Determine the performance of the Hazard Detection AI system system in an unconstrained environment.
Investigate reinforcement learning for continuous learning of the developed Hazard Detection AI system.
Develop a Perception AI system based on deep learning using publicly available data (e.g. KAIST Multi-Spectral Day/Night Data Set (Choi et al., 2018)) to: (a) Predict the intent for different road users e.g. pedestrians, cyclists etc. (b) Detect static road features e.g. road works, road signs etc. and (c) Detect weather condition e.g. fog, rain etc.
Investigate the deep learning framework e.g. TensorFlow or PyTorch.
Build, train, test and validate the neural network.
Determine the performance of the AI in an unconstrained environment.
Investigate reinforcement learning for continuous learning of the developed AI system.
Develop a Hazard Detection AI system for AV using deep learning based on the output from the Perception AI system.
Build, train, test and validate the neural network.
Determine the performance of the Hazard Detection AI system system in an unconstrained environment.
Investigate reinforcement learning for continuous learning of the developed Hazard Detection AI system.
Organisations
People |
ORCID iD |
LUIZ GALVAO (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/T518116/1 | 01/10/2020 | 30/09/2025 | |||
2437901 | Studentship | EP/T518116/1 | 01/10/2020 | 31/12/2023 | LUIZ GALVAO |