Incremental Lifelong Deep Learning for Autonomous Vehicles
By John M. Pierre. 2018
18 citations recorded by the source corpus.
We investigate a deep learning methodology that can produce more accurate behaviors for autonomous vehicles with a much smaller amount of training data than by using supervised learning alone. In this paper, we develop a Correction-Based Incremental Learning (CBIL) algorithm that adds additional training examples strategically selected from cases where the autonomous vehicle has made mistakes, and is repeated over multiple iterations to dramatically improve mean time to failure. CBIL can be thought of as an online mistake bound learning model that reduces the number of training examples needed to define robust decision boundaries, and is trained offline to solve the problem of catastrophic forgetting. We quantitatively benchmark the performance of CBIL using several experiments related to autonomous platooning performed in truck driving simulations and in the laboratory with mobile robots.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Shipeng Yan
- Randy Ardywibowo
- Zhangyang Wang
- Jiangwei Xie
- Zepeng Huo
- Xuming He
- Bobak J. Mortazavi
- Shuai Huang
Citations in the corpus
- General Incremental Learning with Domain-aware Categorical Representations (2022, background): “This paradigm is important in many real world applications [14,22] in which offline learning regularly outperforms the online version.”
- DER: Dynamically Expandable Representation for Class Incremental Learning (2021, background): “Such capability is indispensable for many real-world applications such as the intelligent robot [31], face recognition [19] and autonomous driving [25].”
- VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty (2022, background): “It can be applied to many real-world applications, such as robotics (Thrun & Mitchell, 1995), computer vision (Li et al., 2017), autonomous driving (Pierre, 2018), and healthcare monitoring (Ardywibowo et al., 2019; 2018; Ardywibowo, 2017; Jiang et al., 2019).”
- Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks (2021, methodology): “• Correction Based Incremental Learning (CBIL) [40]: CBIL enables the autonomous vehicle to adapt to the novel scenario by using the least amount of training”