no code implementations • 30 Apr 2024 • Robert McCarthy, Daniel C. H. Tan, Dominik Schmidt, Fernando Acero, Nathan Herr, Yilun Du, Thomas G. Thuruthel, Zhibin Li
This includes a discussion of the exciting benefits LfV methods can offer (e. g., improved generalization beyond the available robot data) and commentary on key LfV challenges (e. g., challenges related to missing information in video and LfV distribution shifts).
no code implementations • 21 Mar 2024 • Fernando Acero, Zhibin Li
Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities.
no code implementations • 21 Dec 2023 • Wenbin Hu, Fernando Acero, Eleftherios Triantafyllidis, Zhaocheng Liu, Zhibin Li
We present a modular framework designed to enable a robot hand-arm system to learn how to catch flying objects, a task that requires fast, reactive, and accurately-timed robot motions.
1 code implementation • 9 Nov 2023 • Georgios Tziafas, Yucheng Xu, Arushi Goel, Mohammadreza Kasaei, Zhibin Li, Hamidreza Kasaei
To address these limitations, we develop a challenging benchmark based on cluttered indoor scenes from OCID dataset, for which we generate referring expressions and connect them with 4-DoF grasp poses.
no code implementations • 28 Sep 2023 • Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li
We evaluate our framework and related intrinsic learning methods in an environment challenged with exploration, and a complex robotic manipulation task challenged by both exploration and long-horizons.
no code implementations • 22 Sep 2023 • Ruyi Feng, Zhibin Li, Bowen Liu, Yan Ding
In this study, we apply the Transformer architecture to traffic tasks, aiming to learn the diversity of trajectories within vehicle populations.
1 code implementation • 31 Aug 2023 • Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam
This paper proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition methods.
no code implementations • 15 Aug 2023 • Kai Yuan, Noor Sajid, Karl Friston, Zhibin Li
We approach this problem by hierarchical generative modelling equipped with multi-level planning-for autonomous task completion-that mimics the deep temporal architecture of human motor control.
1 code implementation • 18 Jul 2023 • Zhibin Li, Piotr Koniusz, Lu Zhang, Daniel Edward Pagendam, Peyman Moghadam
Instead of modelling statistics of features globally (i. e., by the covariance matrix of features), we learn a global field dependency matrix that captures dependencies between fields and then we refine the global field dependency matrix at the instance-wise level with different weights (so-called local dependency modelling) w. r. t.
no code implementations • 30 Jun 2023 • Eleftherios Triantafyllidis, Fernando Acero, Zhaocheng Liu, Zhibin Li
In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation.
no code implementations • 29 Jun 2023 • Wanming Yu, Chuanyu Yang, Christopher McGreavy, Eleftherios Triantafyllidis, Guillaume Bellegarda, Milad Shafiee, Auke Jan Ijspeert, Zhibin Li
Robot motor skills can be learned through deep reinforcement learning (DRL) by neural networks as state-action mappings.
no code implementations • 15 Jun 2023 • Wanyuan Wang, Tianchi Qiao, Jinming Ma, Jiahui Jin, Zhibin Li, Weiwei Wu, Yichuan Jian
Key to the challenge of TSC includes 1) the essential of real-time signal decision, 2) the complexity in traffic dynamics, and 3) the network-level coordination.
1 code implementation • 6 Jun 2023 • Daniel C. H. Tan, Fernando Acero, Robert McCarthy, Dimitrios Kanoulas, Zhibin Li
To address this, we propose a new approach to apply verification methods from control theory to learned value functions.
no code implementations • 9 Mar 2023 • Yucheng Xu, Li Nanbo, Arushi Goel, Zijian Guo, Zonghai Yao, Hamidreza Kasaei, Mohammadreze Kasaei, Zhibin Li
Videos depict the change of complex dynamical systems over time in the form of discrete image sequences.
1 code implementation • 10 Jul 2022 • Litao Yu, Zhibin Li, Jian Zhang, Qiang Wu
Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.
no code implementations • 22 Mar 2022 • Tiantian He, Zhibin Li, Yongshun Gong, Yazhou Yao, Xiushan Nie, Yilong Yin
Non-linear activation functions, e. g., Sigmoid, ReLU, and Tanh, have achieved great success in neural networks (NNs).
1 code implementation • 3 Nov 2021 • Ziwang Fu, Feng Liu, HanYang Wang, Jiayin Qi, Xiangling Fu, Aimin Zhou, Zhibin Li
Firstly, we perform representation learning for audio and video modalities to obtain the semantic features of the two modalities by efficient ResNeXt and 1D CNN, respectively.
1 code implementation • 22 Oct 2021 • Feng Liu, HanYang Wang, Jiahao Zhang, Ziwang Fu, Aimin Zhou, Jiayin Qi, Zhibin Li
Quantitative and Qualitative results are presented on several compound expressions, and the experimental results demonstrate the feasibility and the potential of EvoGAN.
no code implementations • 28 Sep 2021 • Fernando Acero, Kai Yuan, Zhibin Li
To proactively navigate and traverse various terrains, active use of visual perception becomes indispensable.
no code implementations • 20 Jan 2021 • Iordanis Chatzinikolaidis, Zhibin Li
This paper presents a novel approach using sensitivity analysis for generalizing Differential Dynamic Programming (DDP) to systems characterized by implicit dynamics, such as those modelled via inverse dynamics and variational or implicit integrators.
Robotics Systems and Control Systems and Control
no code implementations • 19 Jan 2021 • Timothée Anne, Jack Wilkinson, Zhibin Li
This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion.
no code implementations • 10 Dec 2020 • Chuanyu Yang, Kai Yuan, Qiuguo Zhu, Wanming Yu, Zhibin Li
Achieving versatile robot locomotion requires motor skills which can adapt to previously unseen situations.
1 code implementation • NeurIPS 2020 • Zhibin Li, Jian Zhang, Yongshun Gong, Yazhou Yao, Qiang Wu
We present a model that utilizes linear models with variance and low-rank constraints, to help it generalize better and reduce the number of parameters.
no code implementations • 3 Nov 2020 • Zhibin Li, Litao Yu, Jian Zhang
In this paper, we present a novel data-distribution-aware margin calibration method for a better generalization of the mIoU over the whole data-distribution, underpinned by a rigid lower bound.
no code implementations • 1 Nov 2020 • Zhicheng Wang, Anqiao Li, Yixiao Zheng, Anhuan Xie, Zhibin Li, Jun Wu, Qiuguo Zhu
The NN based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.
no code implementations • 13 May 2020 • Lu Zhang, Jian Zhang, Zhibin Li, Jingsong Xu
Inspired by the fact that spreading and collecting information through the Internet becomes the norm, more and more people choose to post for-profit contents (images and texts) in social networks.
no code implementations • 3 Mar 2020 • Keyhan Kouhkiloui Babarahmati, Carlo Tiseo, Quentin Rouxel, Zhibin Li, Michael Mistry
Robotic teleoperation will allow us to perform complex manipulation tasks in dangerous or remote environments, such as needed for planetary exploration or nuclear decommissioning.
Robotics
no code implementations • 15 Feb 2020 • Zhaole Sun, Kai Yuan, Wenbin Hu, Chuanyu Yang, Zhibin Li
In robotic grasping, objects are often occluded in ungraspable configurations such that no pregrasp pose can be found, eg large flat boxes on the table that can only be grasped from the side.
Robotics
no code implementations • 11 Feb 2020 • Wenbin Hu, Chuanyu Yang, Kai Yuan, Zhibin Li
The performance of learned policy is evaluated on three different tasks: grasping a static target, grasping a dynamic target, and re-grasping.
Robotics
no code implementations • 7 Feb 2020 • Chuanyu Yang, Kai Yuan, Wolfgang Merkt, Taku Komura, Sethu Vijayakumar, Zhibin Li
This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i. e., ankle, hip, foot tilting, and stepping strategies.
no code implementations • 5 Feb 2020 • Ruoshi Wen, Kai Yuan, Qiang Wang, Shuai Heng, Zhibin Li
Regulating contact forces with high precision is crucial for grasping and manipulating fragile or deformable objects.
Robotics
no code implementations • 7 Dec 2019 • Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, Jin-Feng Yi
In this paper, this specific problem is termed as potential passenger flow (PPF) prediction, which is a novel and important study connected with urban computing and intelligent transportation systems.
no code implementations • 2 Jul 2019 • Zhibin Li, Jian Zhang, Qiang Wu, Yongshun Gong, Jin-Feng Yi, Christina Kirsch
In this paper, we formulate our prediction task as a multiple kernel learning problem with missing kernels.
no code implementations • 8 Oct 2017 • Doo Re Song, Chuanyu Yang, Christopher McGreavy, Zhibin Li
This paper presents a deep learning framework that is capable of solving partially observable locomotion tasks based on our novel interpretation of Recurrent Deterministic Policy Gradient (RDPG).