In this paper, we propose a continual learning (CL) approach that adapts to the vehicle CAN-data flexibly and continuously. Our approach is capable of learning from vehicle CAN-bus data in multiple driving scenarios, adapting to the various drifts within each driving scenario. The basis for our approach corresponds to a common solver model and a series of supervisor models. Our solver model extends the memory-aware synapses approach with the use of weight cloning and weighted experience replay. Our supervisor model selects the output of the solver model that corresponds to the driving scenario present at the input. We evaluate our approach using a Tesla Model 3 CAN-data and 8 different driving scenarios. Our evaluation results show that our approach effectively learns multiple driving scenarios sequentially without forgetting the previous knowledge.
Towards Continual Knowledge Learning of Vehicle CAN-data
2023-06-04
1898775 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learning
Springer Verlag | 2023
|CONTINUAL PROACTIVE LEARNING FOR AUTONOMOUS ROBOT AGENTS
Europäisches Patentamt | 2021
|CONTINUAL PROACTIVE LEARNING FOR AUTONOMOUS ROBOT AGENTS
Europäisches Patentamt | 2022
|CONTINUAL PROACTIVE LEARNING FOR AUTONOMOUS ROBOT AGENTS
Europäisches Patentamt | 2022
|