Shenli Yuan

Shenli Yuan

Auto-generated profile, based on publicly available information

Shenli Yuan

Stanford University, Stanford, CA, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
27 January 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MSMingyo Seo
Mingyo Seo
HPH. Andy Park
H. Andy Park
SYShenli Yuan
Shenli Yuan
YZYuke Zhu
Yuke Zhu
LSLuis Sentis
Luis Sentis
Cross-embodiment imitation learning enables policies trained on specific embodiments to transfer across different robots, unlocking the potential for large-scale imitation learning that is both cost-effective and highly reusable. This paper presents LEGATO, a cross-embodiment imitation learning framework for visuomotor skill transfer across varied kinematic morphologies. We introduce a handheld gripper that unifies action and observation spaces, allowing tasks to be defined consistently across robots. We train visuomotor policies on task demonstrations using this gripper through imitation learning, applying transformation to a motion-invariant space for computing the training loss. Gripper motions generated by the policies are retargeted into high-degree-of-freedom whole-body motions using inverse kinematics for deployment across diverse embodiments. Our evaluations in simulation and real-robot experiments highlight the framework's effectiveness in learning and transferring visuomotor skills across various robots.

19 February 2025 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
SYShenli Yuan
Shenli Yuan
SWShaoxiong Wang
Shaoxiong Wang
RPRadhen Patel
Radhen Patel
MTMegha Tippur
Megha Tippur
CYConnor L. Yako
Connor L. Yako
JSJ. Kenneth Salisbury
J. Kenneth Salisbury
Manipulation of objects within a robot's hand is one of the most important challenges in achieving robot dexterity. To address this challenge, Roller Graspers use steerable rolling fingertips. The fingertips impart motions and exert forces to achieve six degree of freedom mobility and closed-loop grasp force control. The design reported here uses image processing from cameras placed inside steerable compliant rollers to track contact conditions and locations. Integration of this data into a controller enables a variety of robust in-hand manipulation capabilities. We demonstrate that the same information can be used to reconstruct object shape. In addition, we show that by converting in-hand manipulation from a discontinuous process, with fingers frequently attaching and detaching from the object surface, to a continuous process, we can implement a convergent control loop that minimizes errors that otherwise accumulate during large object motions. The difference is apparent when comparing the results of an object rotation using a discontinuous finger-gaiting approach, as would be required without rolling fingertips, to the results obtained with continuous rolling. The results suggest that hybrid rolling fingertip and finger-gaiting approaches to manipulation may be a promising future research direction.

5 September 2024 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
SYShenli Yuan
Shenli Yuan
LSLin Shao
Lin Shao
YFYunhai Feng
Yunhai Feng
JSJiatong Sun
Jiatong Sun
TXTeng Xue
Teng Xue
JSJ. Kenneth Salisbury
J. Kenneth Salisbury
Robot in-hand manipulation is an important skill for robots to carry out sophisticated tasks that require moving the grasped object within hand. In this work, we present the Roller Grasper V3, a non-anthropomorphic robot grasper with a steerable roller on each of its four fingertips, and a manipulation architecture that enables the Roller Grasper V3 to achieve full 6-DoF manipulation of the grasped object in $SE(3)$ . The manipulation architecture consists of a high-level planner that searches for a feasible path with waypoints for the object to be manipulated, and a low-level control policy that is used to navigate the object in between the adjacent waypoints. The method was experimentally validated on the Roller Grasper V3 to manipulate multiple objects with different geometries and topologies.

26 February 2023 in arXiv
Verified
Preprint
Open access
PDF file
SYShenli Yuan
Shenli Yuan
Lingjie KongLingjie Kong
Lingjie Kong
JGJiushuang Guo
Jiushuang Guo
Automatic music transcription (AMT) aims to convert raw audio to symbolic music representation. As a fundamental problem of music information retrieval (MIR), AMT is considered a difficult task even for trained human experts due to overlap of multiple harmonics in the acoustic signal. On the other hand, speech recognition, as one of the most popular tasks in natural language processing, aims to translate human spoken language to texts. Based on the similar nature of AMT and speech recognition (as they both deal with tasks of translating audio signal to symbolic encoding), this paper investigated whether a generic neural network architecture could possibly work on both tasks. In this paper, we introduced our new neural network architecture built on top of the current state-of-the-art Onsets and Frames, and compared the performances of its multiple variations on AMT task. We also tested our architecture with the task of speech recognition. For AMT, our models were able to produce better results compared to the model trained using the state-of-art architecture; however, although similar architecture was able to be trained on the speech recognition task, it did not generate very ideal result compared to other task-specific models.

18 November 2020 in arXiv
Verified
Preprint
Open access
PDF file
SYShenli Yuan
Shenli Yuan
LSLin Shao
Lin Shao
CYConnor L. Yako
Connor L. Yako
AGAlex Gruebele
Alex Gruebele
JSJ. Kenneth Salisbury
J. Kenneth Salisbury
The ability to perform in-hand manipulation still remains an unsolved problem; having this capability would allow robots to perform sophisticated tasks requiring repositioning and reorienting of grasped objects. In this work, we present a novel non-anthropomorphic robot grasper with the ability to manipulate objects by means of active surfaces at the fingertips. Active surfaces are achieved by spherical rolling fingertips with two degrees of freedom (DoF) -- a pivoting motion for surface reorientation -- and a continuous rolling motion for moving the object. A further DoF is in the base of each finger, allowing the fingers to grasp objects over a range of size and shapes. Instantaneous kinematics was derived and objects were successfully manipulated both with a custom handcrafted control scheme as well as one learned through imitation learning, in simulation and experimentally on the hardware.