Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
PyPose v0.6: The Imperative Programming Interface for Robotics
Published in IROS Workshop, 2023
PyPose is an open-source library for robot learning. It combines a learning-based approach with physics-based optimization, which enables seamless end-to-end robot learning. It has been used in many tasks due to its meticulously designed application programming interface (API) and efficient implementation. From its initial launch in early 2022, PyPose has experienced significant enhancements, incorporating a wide variety of new features into its platform. To satisfy the growing demand for understanding and utilizing the library and reduce the learning curve of new users, we present the fundamental design principle of the imperative programming interface, and showcase the flexible usage of diverse functionalities and modules using an extremely simple Dubins car example. We also demonstrate that the PyPose can be easily used to navigate a real quadruped robot with a few lines of code.
Recommended citation: Z. Zhan et al., PyPose v0.6: The imperative programming interface for robotics. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop, 2023. http://rokeeeto-li.github.io/files/pypose_v06.pdf
Data-driven Shape Sensing of Continuum Dexterous Manipulators Using Embedded Capacitive Sensor
Published in 2023 IEEE SENSORS, 2023
We propose a novel inexpensive embedded capacitive sensor (ECS) for sensing the shape of Continuum Dexterous Manipulators (CDMs). Our approach addresses some limitations associated with the prevalent Fiber Bragg Grating (FBG) sensors, such as temperature sensitivity and high production costs. ECSs are calibrated using a vision-based system. The calibration of the ECS is performed by a recurrent neural network that uses the kinematic data collected from the vision-based system along with the uncalibrated data from ECSs. We evaluated the performance on a 3D printed prototype of a cable-driven CDM with multiple markers along its length. Using data from three ECSs along the length of the CDM, we computed the angle and position of its tip with respect to its base and compared the results to the measurements of the visual-based system. We found a 6.6% tip position error normalized to the length of the CDM. The work shows the early feasibility of using ECSs for shape sensing and feedback control of CDMs and discusses potential future improvements.
Recommended citation: Q. Li, W. Wang, J. Liu, A. Jain, and M. Armand, “Data-driven Shape Sensing of Continuum Dexterous Manipulators Using Embedded Capacitive Sensor,” in 2023 IEEE SENSORS, Vienna, Austria: IEEE, Oct. 2023, pp. 1–4. doi: 10.1109/SENSORS56945.2023.10324929. http://rokeeeto-li.github.io/files/2023-11-28-CDM-ECS.pdf
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Statistical Learning for Engineers
Graduate course, Johns Hopkins University, Mechanical Engineering Department, 2022
This course will discuss general aspects of machine and reinforcement learning, which is suitable for students in different fields of interest, though the primary applications include robotics engineering. Topics that will be covered include: core mathematics necessary, core principles for supervised and unsupervised learning (e.g., linear regression, logistic regression, Bayes nets, EM, and so on), and for reinforcement learning (e.g., Markov decision process, dynamic programming, etc.).