Michael C. Yip

Michael C. Yip

Auto-generated profile, based on publicly available information

Michael C. Yip

Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 August 2020 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
AQAhmed Hussain Qureshi
Ahmed Hussain Qureshi
YMYinglong Miao
Yinglong Miao
ASAnthony Simeonov
Anthony Simeonov
MYMichael C. Yip
Michael C. Yip
This article describes motion planning networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning problems.MPNet uses neural networks to learn general near-optimal heuristics for path planning in seen and unseen environments. It takes environment information such as raw point cloud from depth sensors, as well as a robot's initial and desired goal configurations and recursively calls itself to bidirectionally generate connectable paths. In addition to finding directly connectable and near-optimal paths in a single pass, we show that worst-case theoretical guarantees can be proven if we merge this neural network strategy with classical sample-based planners in a hybrid approach while still retaining significant computational and optimality improvements. To train the MPNet models, we present an active continual learning approach that enables MPNet to learn from streaming data and actively ask for expert demonstrations when needed, drastically reducing data for training. We validate MPNet against gold-standard and state-of-the-art planning methods in a variety of problems from two-dimensional to seven-dimensional robot configuration spaces in challenging and cluttered environments, with results showing significant and consistently stronger performance metrics, and motivating neural planning in general as a modern strategy for solving motion planning problems efficiently.

1 June 2019 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
JZJun Zhang
Jun Zhang
JSJun Sheng
Jun Sheng
COCiaran T. O'NEill
Ciaran T. O'NEill
CWConor J. Walsh
Conor J. Walsh
RWRobert Wood
Robert Wood
MYMichael C. Yip
Michael C. Yip
Robotic artificial muscles are a subset of artificial muscles that are capable of producing biologically inspired motions useful for robot systems, i.e., large power-to-weight ratios, inherent compliance, and large range of motions. These actuators, ranging from shape memory alloys to dielectric elastomers, are increasingly popular for biomimetic robots as they may operate without using complex linkage designs or other cumbersome mechanisms. Recent achievements in fabrication, modeling, and control methods have significantly contributed to their potential utilization in a wide range of applications. However, no survey paper has gone into depth regarding considerations pertaining to their selection, design, and usage in generating biomimetic motions. In this paper, we discuss important characteristics and considerations in the selection, design, and implementation of various prominent and unique robotic artificial muscles for biomimetic robots, and provide perspectives on next-generation muscle-powered robots.

13 November 2020 in Science Advances
Verified
Journal Article
Open access
PDF file
HOHongseok Oh
Hongseok Oh
GYGyu-Chul Yi
Gyu-Chul Yi
MYMichael Yip
Michael Yip
SDShadi A. Dayeh
Shadi A. Dayeh
A single thin-film transistor senses, amplifies, and multiplexes force to sense slip and close the loop in robotic gripping.

31 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YLYang Li
Yang Li
FRFlorian Richter
Florian Richter
JLJingpei Lu
Jingpei Lu
EFEmily K. Funk
Emily K. Funk
RORyan K. Orosco
Ryan K. Orosco
MYMichael C. Yip
Michael C. Yip
Traditional control and task automation have been successfully demonstrated in a variety of structured, controlled environments through the use of highly specialized modeled robotic systems in conjunction with multiple sensors. However, the application of autonomy in endoscopic surgery is very challenging, particularly in soft tissue work, due to the lack of high-quality images and the unpredictable, constantly deforming environment. In this letter, we propose a novel surgical perception framework, SuPer, for surgical robotic control. This framework continuously collects 3D geometric information that allows for mapping a deformable surgical field while tracking rigid instruments within the field. To achieve this, a model-based tracker is employed to localize the surgical tool with a kinematic prior in conjunction with a model-free tracker to reconstruct the deformable environment and provide an estimated point cloud as a mapping of the environment. The proposed framework was implemented on the da Vinci Surgical System in real-time with an end-effector controller where the target configurations are set and regulated through the framework. Our proposed framework successfully completed soft tissue manipulation tasks with high accuracy. The demonstration of this novel framework is promising for the future of surgical autonomy. In addition, we provide our dataset for further surgical research.

24 February 2017 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
MYMichael C. Yip
Michael C. Yip
GNGunter Niemeyer
Gunter Niemeyer
Robotics have long sought an actuation technology comparable to or as capable as biological muscle tissue. Natural muscles exhibit a high power-to-weight ratio, inherent compliance and damping, fast action, and a high dynamic range. They also produce joint displacements and forces without the need for gearing or additional hardware. Recently, supercoiled commercially available polymer threads (sewing thread or nylon fishing lines) have been used to create significant mechanical power in a muscle-like form factor. Heating and cooling the polymer threads causes contraction and expansion, which can be utilized for actuation. In this paper, we describe the working principle of supercoiled polymer (SCP) actuation and explore the controllability and properties of these threads. We show that under appropriate environmental conditions, the threads are suitable as a building block for a controllable artificial muscle. We leverage off-the-shelf silver-coated threads to enable rapid electrical heating while the low thermal mass allows for rapid cooling. We utilize both thermal and thermomechanical models for feed-forward and feedback control. The resulting SCP actuator regulates to desired force levels in as little as 28 ms. Together with its inherent stiffness and damping, this is sufficient for a position controller to execute large step movements in under 100 ms. This controllability, high performance, the mechanical properties, and the extremely low material cost are indicative of a viable artificial muscle.

3 March 2020 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
NDNikhil Das
Nikhil Das
MYMichael Yip
Michael Yip
This article demonstrates that collision detection-intensive applications such as robotic motion planning may be accelerated by performing collision checks with a machine learning model. We propose Fastron, a learning-based algorithm, to model a robot’s configuration space to be used as a proxy collision detector in place of standard geometric collision checkers. We demonstrate that leveraging the proxy collision detector results in up to an order of magnitude faster performance in robot simulation and planning than state-of-the-art collision detection libraries. Our results show that Fastron learns a model more than 100 times faster than a competing C-space modeling approach, while also providing theoretical guarantees of learning convergence. Using the open motion planning libraries (OMPLs), we were able to generate initial motion plans across all experiments with varying robot and environment complexities and workspace obstacle locations. With Fastron, we can repeatedly generate new motion plans at a 56 Hz rate, showing its application toward autonomous surgical assistance task in shared environments with human-controlled manipulators. All performance gains were achieved despite using only CPU-based calculations, suggesting further computational gains with a GPU approach that can parallelize tensor algebra. Code is available online.