Representation and POMDP
The real world is a complex environment with multiple objects and agents interacting with each other. The sensor observations a robot can receive is usually high dimensional and time sequential. I'm interested in developing theories and algorithms that can extract useful information from the complex environment for better subsequent decision and control tasks. I focus on the following important topics: (1) Representation learning: Learn appropriate representation of the environments; (2) POMDP: Model the environment as a partially observable Markov decision process (POMDP) and develop learning techniques to solve it; (3) Estimation: Emerge techniques of estimation theory from control to better estimate the true state of the environment.
Representation Learning
|
POMDP
|
Estimation
|
Related Publications
- W. Cao, J. Chen, J. Duan, SE. Li, Y. Lyu, Z. Gu, Y. Zhang, "Reinforced Optimal Estimator", Modeling, Estimation and Control Conference (MECC), 2021.
- J. Chen, Y. Shimizu, L. Sun, M. Tomizuka, W. Zhan, "Constrained Iterative LQG for Real-Time Chance-Constrained Gaussian Belief Space Planning", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
- J. Chen, S. Li, and M. Tomizuka, “Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning”, IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2021.
- J. Chen, Z. Xu, and M. Tomizuka, “End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.
- C. Tang, J. Chen, and M. Tomizuka, “Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network”, International Conference on Robotics and Automation (ICRA), 2019.
- B. Yuan, J. Chen, W. Zhang, and S. McMains, “Iterative Cross Learning on Noisy Labels”, IEEE Winter Conf. on Applications of Computer Vision (WACV), 2018.
- L. Xin, P. Wang, C-Y. Chan, J. Chen, S. Li and B. Cheng, “Intention-Aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks”, IEEE Intelligent Transportation Systems Conference (ITSC), 2018.