Robotics PhD at Stanford University helping robots perceive through touch

My research focuses on how to enable robots to use the sense of touch to execute tasks more effectively in unstructured settings such as our homes. I develop robots and tactile sensors with the goal of facilitating perception of the environment through contacts. This includes design of robot end-effectors or sensors that can safely and quickly make contact with light objects, to algorithms that are able to integrate sensor information through time to make sense of the environment with the goal of grasping and exploration in clutter.

I am part of the Biomimetric and Dexterous Manipulation Lab, advised by Prof. Mark Cutkosky. I am also currently part of the NVIDIA Seattle Robotics Lab where I am investigating methods to transfer robot skills learned in simulation to the real world (sim2real) by making simulator dynamics more realistic. Prior to my PhD, I was a Robotics System Engineer at Flexiv Robotics Inc. developing the mechatronics and controls of a 7 degrees-of-freedom torque-controlled robot arm for industrial task automation. I completed my undergraduate in Electrical Engineering and Computer Science at UC Berkeley with a focus in mechatronics and signals and systems.

Contact:
mlinyang@stanford.edu
Google Scholar

Michael Lin smiling, wearing jacket and blue lake in background.

Latest Research

A GIF image showing a robot gripper moving inside a cabinet and making contact with four spice jars quickly, and then grasping one of the spice jars.

Whisker-Inspired Tactile Sensing for Contact Localization on Robot Manipulators

Michael A. Lin, Emilio Reyes, Jeannette Bohg, Mark Cutkosky.

This work presents the design and modelling of whisker-inspired sensors that attach to the surface of a robot manipulator to sense its surrounding through light contacts. We obtain a sensor model using a calibration process that applies to straight and curved whiskers. We then propose a sensing algorithm using Bayesian filtering to localize contact points. The algorithm combines the accurate proprioceptive sensing of the robot and sensor readings from the deflections of the whiskers. Our results show that our algorithm is able to track contact points with sub-millimeter accuracy, outperforming a baseline method. Finally, we demonstrate our sensor and perception method in a real-world system where a robot moves in between free-standing objects and uses the whisker sensors to track contacts tracing object contours.

A GIF image showing a robot gripper moving inside a cabinet and making contact with four spice jars quickly, and then grasping one of the spice jars.

Exploratory Hand: Leveraging Safe Contact to Facilitate Manipulation in Cluttered Spaces

Michael A. Lin, Rachel Thomasson, Gabriela Uribe, Hojung Choi and Mark R. Cutkosky

We present a new gripper and exploration approach that uses an exploratory finger with very low reflected inertia for probing and grasping objects quickly and safely in unstructured environments. Equipped with sensing and force control, the gripper allows a robot to leverage contact information to accurately estimate object location through a particle filtering algorithm and also grasp objects with location uncertainty based on a contact-first approach. This publication is still under review so it is not yet available.

A robot arm with a custom designed 2-DOF wrist that wears a white sleeve with soft pneumatic sensors. The robot is reaching into a fridge drawer to retrieve a pear.

A Stretchable Tactile Sleeve for Reaching into Cluttered Spaces

Alexander M. Gruebele, Michael A. Lin, Dane Brouwer, Shenli Yuan, Andrew Zerbe and Mark R. Cutkosky

A highly conformable stretchable sensory skin made entirely of soft components. The skin uses pneumatic taxels and stretchable channels to conduct pressure signals to off-board MEMs pressure sensors. The skin is able to resolve forces down to 0.01N and responds to vibrations up to 200 Hz. We apply the skin to a 2 degree-of-freedom robotic wrist with intersecting axes for manipulation in constrained spaces, and show that it has sufficient sensitivity and bandwidth to detect the onset of sliding as the robot contacts objects. We demonstrate the skin in object acquisition tasks in a tightly constrained environment for which extraneous contacts are unavoidable.

Skills Highlight

Robotics
Robot Arm Manipulation (Operational Space Control) / State Estimation (Particle Fitlering/EKF/SLAM) / System Integration (ROS) / Physics Simulation (PyBullet, MuJoCo, NVIDIA Isaac Gym) / OpenCV
Machine Learning
Deep Reinforcement Learning / Deep Learning Models for Visual and Sequential data (CNN, RNN, LSTM) / Gaussian Process Regression
Programming
Python / C++ / C Language / PyTorch
Embedded Systems
State Machines / Sync and Async Serial Comm. / BLE / Ethernet Fieldbus comm
Hardware
Brushless motor control / Circuit design / CAD modeling