no code implementations • 20 Jan 2024 • Soham Shanbhag, Dong Eui Chang
Conventional techniques involving machine learning based observers on systems evolving on Lie groups involve designing charts for the Lie group, training a machine learning based observer for each chart, and switching between the trained models based on the state of the system.
no code implementations • 20 Jan 2024 • Soham Shanbhag, Dong Eui Chang
We propose a modification technique for discrete time systems for exponentially fast convergence to compact sets.
no code implementations • 20 Jan 2024 • Soham Shanbhag, Dong Eui Chang
We propose a globally exponentially convergent observer for the dynamical system evolving on matrix Lie groups with bounded velocity with unknown bound.
no code implementations • 20 Jan 2024 • Soham Shanbhag, Dong Eui Chang
Rigid body systems usually consider measurements of the pose of the body using onboard cameras/LiDAR systems, that of linear acceleration using an accelerometer and of angular velocity using an IMU.
1 code implementation • 12 May 2022 • Fanchen Bu, Dong Eui Chang
In particular, inspired by a numerical integration method on manifolds called Feedback Integrators, we propose to instantiate it on the tangent bundle of the Stiefel manifold for the first time.
no code implementations • 27 May 2021 • Tianqi Wang, Dong Eui Chang
This paper presents a vision-based modularized drone racing navigation system that uses a customized convolutional neural network (CNN) for the perception module to produce high-level navigation commands and then leverages a state-of-the-art planner and controller to generate low-level control commands, thus exploiting the advantages of both data-based and model-based approaches.
1 code implementation • 29 Dec 2020 • Xiaowei Xing, Dong Eui Chang
The paper develops the Adaptive Dynamic Programming Toolbox (ADPT), which solves optimal control problems for continuous-time nonlinear systems.
no code implementations • 8 Jul 2020 • Fanchen Bu, Dong Eui Chang
Experience replay enables online reinforcement learning agents to store and reuse the previous experiences of interacting with the environment.
no code implementations • 16 Jul 2019 • Tianqi Wang, Dong Eui Chang
We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering control output.
no code implementations • 16 Jul 2019 • Xiaowei Xing, Dong Eui Chang
Deep reinforcement learning trains neural networks using experiences sampled from the replay buffer, which is commonly updated at each time step.
Robotics Systems and Control Systems and Control
no code implementations • 15 Jul 2019 • Wonshick Ko, Dong Eui Chang
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory.
1 code implementation • 17 Jun 2019 • Muhammad Usama, Dong Eui Chang
We introduce entropy-based exploration (EBE) that enables an agent to explore efficiently the unexplored regions of state space.
no code implementations • 2 Apr 2019 • Chang Sik Lee, Dong Eui Chang
An energy based approach for stabilizing a mechanical system has offered a simple yet powerful control scheme.
no code implementations • 28 Feb 2019 • Ce Ju, Zheng Wang, Cheng Long, Xiao-Yu Zhang, Gao Cong, Dong Eui Chang
Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.)
Robotics I.2.9; I.2.0
no code implementations • 22 Nov 2018 • Muhammad Usama, Dong Eui Chang
Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures.
no code implementations • 5 Oct 2016 • Anthony Caterini, Dong Eui Chang
However, the representation is non-standardized, and the gradient calculation methods are often performed using component-based approaches that break parameters down into scalar units, instead of considering the parameters as whole entities.
no code implementations • 15 Aug 2016 • Anthony L. Caterini, Dong Eui Chang
In this paper, a geometric framework for neural networks is proposed.