Tianyi Xiang

Profili

I’m a Robotics master student from Yale University, major in mechanical engineering & material science. I like Applied Motion Planning, Perception, and Vision Language Model with practical robots!

The goal of my work is to enable people to intuitively control or work alongside robot manipulation platforms to perform critical tasks deemed unsuitable, undesirable, understaffed, or unsafe for people, such as industrial robotics arm assembly, remote teleoperation programming, soft robotics, and even control with virtual reality. I use interdisciplinary techniques across robotics and computer science, including motion planning, machine learning, visual-perception, Vision-language model,virtual reality, communication system to formulate and validate solutions within problems in diverse fields.

I always consider how to bring a true agent into household?! And I consider it as a dynamic system as follow.

project_proposal

To achieve this goal, I have divided it into four key areas, each benefiting from my past experiences:

  • (A) Perception – Category level Object Pose & Geometry & Mesh Estimation, better with Large Vision Modal.

  • (B) Vision Language Modal – perform as robot’s [brain]. Feed all stream coming from perception, task planner, achieving replanning in loop.

  • (C) Basic Dyanmics - general sampling based motion planning, with kinodynamics, deterity manipulation in special case.

  • (D) Multimodel-Sensor Perception - Visual sensor, along with tactile sensor such as TENG, Soft electronic, Visual tactile sensor.

Contact: Tianyi.Xiang@yale.edu

My Resume

You can find my CV here:Tianyi’s CV

Publications:

[1] “Real-to-Sim via End-to-End Differentiable Simulation and Rendering”
Yifan Zhu, Tianyi Xiang, Aaron Dollar, Zherong Pan
IEEE Robotics and Automation Letters (RAL), Manuscript submitted for publication
Paper

[2]“A Novel Approach to Grasping Control of Soft Robotic Grippers based on Digital Twin”
Tianyi Xiang, Borui Li, Quan Zhang, March Leach, Enggee Lim
29th International Conference on Automation and Computing (ICAC 2024)
Paper

[3] “Development of a Simple and Novel Digital Twin Framework for Industrial Robots in Intelligent Robotics Manufacturing”
Tianyi Xiang, Borui Li, Quan Zhang
20th International Conference on Automation Science and Engineering (CASE 2024)
Paper; Video

[4] “High performance (Zn₀.₅Mg₀.₅)TiO₃ ceramics based composite films for powering multi-mode translation unit and human motion monitoring”
Xie, B., Xie, Y., Ma, Y., Luo, N., Tianyi Xiang, et al.
ACS Applied Materials & Interfaces, Manuscript submitted for publication (2024)

Projects Video & Pictures

Real-to-Sim via End-to-End Differentiable Simulation and Rendering

screenshot

Liquid Manipulation: Category-level pose & dimension detector with pouring action optimizer

Forked PDDLstream Task and Motion planning (TAMP) online replanning.

(simulation forked from Caelan Reed Garrett LTAMP)

Behaviour cloning (BC) learning-based Block Pushing task

Vision-learning based Soft Actuator Grasping Control within Digital Twin

OpenCV based Soft Actuator Grasping Control in Unity3D

Simple and Novel Motion Planning Digital Twin Framework for Industrial Robot

Autonomous tracking DIY Mars Rover Design

Tactile Sensing achieving human motion monitoring

Tactile Sensing

ROS SLAM AGV navigation with Adaptive Monte Carlo Localization (AMCL)

AGV with PLC control optimisation simulation

AGV optimisation