Search Results for author: Xingyu Lin

Found 19 papers, 5 papers with code

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation

no code implementations15 Mar 2024 Carmelo Sferrazza, Dun-Ming Huang, Xingyu Lin, Youngwoon Lee, Pieter Abbeel

Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology.

Any-point Trajectory Modeling for Policy Learning

no code implementations28 Dec 2023 Chuan Wen, Xingyu Lin, John So, Kai Chen, Qi Dou, Yang Gao, Pieter Abbeel

Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning.

Trajectory Modeling Transfer Learning

Learning Generalizable Tool-use Skills through Trajectory Generation

no code implementations29 Sep 2023 Carl Qi, Sarthak Shetty, Xingyu Lin, David Held

We propose to learn a generative model of the tool-use trajectories as a sequence of point clouds, which generalizes to different tool shapes.

Deformable Object Manipulation

SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks

no code implementations7 Jul 2023 Xingyu Lin, John So, Sashwat Mahalingam, Fangchen Liu, Pieter Abbeel

In this work, we present a focused study of the generalization capabilities of the pre-trained visual representations at the categorical level.

Imitation Learning

Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking

no code implementations19 Feb 2023 Zixuan Huang, Xingyu Lin, David Held

In this work, we propose a self-supervised method to finetune a mesh reconstruction model in the real world.

Self-Supervised Learning

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation

no code implementations27 Oct 2022 Xingyu Lin, Carl Qi, Yunchu Zhang, Zhiao Huang, Katerina Fragkiadaki, Yunzhu Li, Chuang Gan, David Held

Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels.

Deformable Object Manipulation

Mesh-based Dynamics with Occlusion Reasoning for Cloth Manipulation

no code implementations6 Jun 2022 Zixuan Huang, Xingyu Lin, David Held

We evaluate our system both on cloth flattening as well as on cloth canonicalization, in which the objective is to manipulate the cloth into a canonical pose.

Pose Estimation

Self-supervised Transparent Liquid Segmentation for Robotic Pouring

1 code implementation3 Mar 2022 Gautham Narayan Narasimhan, Kai Zhang, Ben Eisner, Xingyu Lin, David Held

Liquid state estimation is important for robotics tasks such as pouring; however, estimating the state of transparent liquids is a challenging problem.

Segmentation

TransLog: A Unified Transformer-based Framework for Log Anomaly Detection

no code implementations31 Dec 2021 Hongcheng Guo, Xingyu Lin, Jian Yang, Yi Zhuang, Jiaqi Bai, Tieqiao Zheng, Bo Zhang, Zhoujun Li

Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage.

Anomaly Detection

Learning Visible Connectivity Dynamics for Cloth Smoothing

1 code implementation21 May 2021 Xingyu Lin, YuFei Wang, Zixuan Huang, David Held

Robotic manipulation of cloth remains challenging for robotics due to the complex dynamics of the cloth, lack of a low-dimensional state representation, and self-occlusions.

Deformable Object Manipulation Inductive Bias

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation

2 code implementations14 Nov 2020 Xingyu Lin, YuFei Wang, Jake Olkin, David Held

Further, we evaluate a variety of algorithms on these tasks and highlight challenges for reinforcement learning algorithms, including dealing with a state representation that has a high intrinsic dimensionality and is partially observable.

Benchmarking Deformable Object Manipulation +4

ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning

1 code implementation13 Nov 2020 YuFei Wang, Gautham Narayan Narasimhan, Xingyu Lin, Brian Okorn, David Held

Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning.

Multi-Goal Reinforcement Learning Object +2

Adaptive Auxiliary Task Weighting for Reinforcement Learning

1 code implementation NeurIPS 2019 Xingyu Lin, Harjatin Baweja, George Kantor, David Held

Reinforcement learning is known to be sample inefficient, preventing its application to many real-world problems, especially with high dimensional observations like images.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning without Ground-Truth State

no code implementations20 May 2019 Xingyu Lin, Harjatin Singh Baweja, David Held

However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations.

reinforcement-learning Reinforcement Learning (RL) +1

Adaptive Variance for Changing Sparse-Reward Environments

no code implementations15 Mar 2019 Xingyu Lin, Pengsheng Guo, Carlos Florensa, David Held

Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration.

Learning Robust Object Recognition Using Composed Scenes from Generative Models

no code implementations22 May 2017 Hao Wang, Xingyu Lin, Yimeng Zhang, Tai Sing Lee

Trained on imagined occluded scenarios under the object persistence constraint, our network discovered more subtle and localized image features that were neglected by the original network for object classification, obtaining better separability of different object classes in the feature space.

Object Object Recognition

Transfer of View-manifold Learning to Similarity Perception of Novel Objects

no code implementations31 Mar 2017 Xingyu Lin, Hao Wang, Zhihao LI, Yimeng Zhang, Alan Yuille, Tai Sing Lee

We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our visual experience.

Metric Learning Object

Cannot find the paper you are looking for? You can Submit a new open access paper.