Yunhai Han

Yunhai Han

Auto-generated profile, based on publicly available information

Yunhai Han

Georgia Institute of Technology, Atlanta, GA, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
7 June 2024 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
YHYunhai Han
Yunhai Han
KYKelin Yu
Kelin Yu
RBRahul Batra
Rahul Batra
NBNathan Boyd
Nathan Boyd
CMChaitanya Mehta
Chaitanya Mehta
YZYe Zhao
Ye Zhao
Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions with a gripper, unknown object dynamics and geometries. In this study, we propose a transformer-based robotic grasping framework for rigid grippers that leverage tactile and visual information for safe object grasping. Specifically, the transformer models learn physical feature embeddings with sensor feedback through performing two predefined explorative actions (pinching and sliding) and predict a grasping outcome through a multilayer perceptron with a given grasping strength. Using these predictions, the gripper predicts a safe grasping strength via inference. Compared with convolutional recurrent networks, the transformer models can capture the long-term dependencies across the image sequences and process spatial–temporal features simultaneously. We first benchmark the transformer models on a public dataset for slip detection. Following that, we show that the transformer models outperform a CNN + LSTM model in terms of grasping accuracy and computational efficiency. We also collect a new fruit grasping dataset and conduct online grasping experiments using the proposed framework for both seen and unseen fruits. In addition, we extend our model to objects with different shapes and demonstrate the effectiveness of our pretrained model trained on our large-scale fruit dataset.

16 August 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YHYunhai Han
Yunhai Han
ZCZhenyang Chen
Zhenyang Chen
KWKyle A Williams
Kyle A Williams
HRHarish Ravichandar
Harish Ravichandar
When human acquire physical skills (e.g., tool use) from experts, we tend to first learn from merely observing the expert. But this is often insufficient. We then engage in practice, where we try to emulate the expert and ensure that our actions produce similar effects on our environment. Inspired by this observation, we introduce C ombining IM itation and E mulation for Motion R efinement (CIMER) – a two-stage framework to learn dexterous prehensile manipulation skills from state-only observations. CIMER's first stage involves imitation: simultaneously encode the complex interdependent motions of the robot hand and the object in a structured dynamical system. This results in a reactive motion generation policy that provides a reasonable motion prior , but lacks the ability to reason about contact effects due to the lack of action labels. The second stage involves emulation: learn a motion refinement policy via reinforcement that adjusts the robot hand's motion prior such that the learned object motion is reenacted. CIMER is both task-agnostic (no task-specific reward design or shaping) and intervention-free (no additional teleoperated or labeled demonstrations). Detailed experiments with prehensile dexterity reveal that i) imitation alone is insufficient, but adding emulation drastically improves performance, ii) CIMER outperforms existing methods in terms of sample efficiency and the ability to generate realistic and stable motions, iii) CIMER can either zero-shot generalize or learn to adapt to novel objects from the YCB dataset, even outperforming expert policies trained with action labels in most cases.

6 December 2021 in IEEE Control Systems Letters
Verified
Journal Article
Closed access
YHYunhai Han
Yunhai Han
SMSonia Martinez
Sonia Martinez
This letter proposes an algorithmic method to verify differential privacy for estimation mechanisms with performance guarantees. Differential privacy makes it hard to distinguish outputs of a mechanism produced by adjacent inputs. While obtaining theoretical conditions that guarantee differential privacy may be possible, evaluating these conditions in practice can be hard. This is especially true for estimation mechanisms that take values in continuous spaces, as this requires checking for an infinite set of inequalities. Instead, our verification approach consists of testing the differential privacy condition for a suitably chosen finite collection of events at the expense of some information loss. More precisely, our data-driven, test framework for continuous range mechanisms first finds a highly-likely, compact event set, as well as a partition of this event, and then evaluates differential privacy wrt this partition. This results into a type of differential privacy with high confidence, which we are able to quantify precisely. This approach is then used to evaluate the differential-privacy properties of the recently proposed $W_{2}$ Moving Horizon Estimator. We confirm its properties, while comparing its performance with alternative approaches in simulation.

28 February 2021 in arXiv
Verified
Preprint
Open access
PDF file
YHYunhai Han
Yunhai Han
Fei LiuFei Liu
Fei Liu
MYMichael C. Yip
Michael C. Yip
The control and task automation of robotic surgical system is very challenging, especially in soft tissue manipulation, due to the unpredictable deformations. Thus, an accurate simulator of soft tissues with the ability of interacting with robot manipulators is necessary. In this work, we propose a novel 2D simulation framework for tool-tissue interaction. This framework continuously tracks the motion of manipulator and simulates the tissue deformation in presence of collision detection. The deformation energy can be computed for the control and planning task.