You Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
You Zhou has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Tamim Asfour
Karlsruhe Institute of Technology, Karlsruhe, Germany
6 shared publications - Eren Erdal Aksoy
Halmstad University
2 shared publications - Mirko Wachter
Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany
2 shared publications - Athanasios C. Dometios
School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece
1 shared publication - Costas S. Tzafestas
National Technical University of Athens (NTUA)
1 shared publication - Dongmei Xu
Department of Nephrology, Shandong Provincial Qianfoshan Hospital, Shandong University, Jinan, China
1 shared publication
Latest Publications
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 8431-8438
Learning to Sequence and Blend Robot Skills via Differentiable Optimization
In contrast to humans and animals who naturally execute seamless motions, learning and smoothly executing sequences of actions remains a challenge in robotics. This letter introduces a novel skill-agnostic framework that learns to sequence and blend skills based on differentiable optimization. Our approach encodes sequences of previously-defined skills as quadratic programs (QP), whose parameters determine the relative importance of skills along the task. Seamless skill sequences are then learned from demonstrations by exploiting differentiable optimization layers and a tailored loss formulated from the QP optimality conditions. Via the use of differentiable optimization, our work offers novel perspectives on multitask control. We validate our approach in a pick-and-place scenario with planar robots, a pouring experiment with a real humanoid robot, and a bimanual sweeping task with a human model.
- 17 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 8431-8438
Learning to Sequence and Blend Robot Skills via Differentiable Optimization
In contrast to humans and animals who naturally execute seamless motions, learning and smoothly executing sequences of actions remains a challenge in robotics. This letter introduces a novel skill-agnostic framework that learns to sequence and blend skills based on differentiable optimization. Our approach encodes sequences of previously-defined skills as quadratic programs (QP), whose parameters determine the relative importance of skills along the task. Seamless skill sequences are then learned from demonstrations by exploiting differentiable optimization layers and a tailored loss formulated from the QP optimality conditions. Via the use of differentiable optimization, our work offers novel perspectives on multitask control. We validate our approach in a pick-and-place scenario with planar robots, a pouring experiment with a real humanoid robot, and a bimanual sweeping task with a human model.
- Open Access
- 6 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 27 (2) , 22-32
Movement Primitive Learning and Generalization: Using Mixture Density Networks
- 6 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 27 (2) , 22-32
Open AccessMovement Primitive Learning and Generalization: Using Mixture Density Networks
- Open Access
- 30 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 26 (4) , 108-121
ARMAR-6: A High-Performance Humanoid for Human-Robot Collaboration in Real-World Scenarios
A major goal of humanoid robotics is to enable safe and reliable human-robot collaboration in realworld scenarios. In this article, we present ARMAR-6, a new high-performance humanoid robot for various tasks, including but not limited to grasping, mobile manipulation, integrated perception, bimanual collaboration, compliant-motion execution, and natural language understanding. We describe how the requirements arising from these tasks influenced our major design decisions, resulting in vertical integration during the joint hardware and software development phases. In particular, the entire hardware-including its structure, sensor-actuator units, and low-level controllers-as well as its perception, grasping and manipulation skills, task coordination, and the entire software architecture were all developed by one team of engineers. Component interaction is facilitated by our software framework ArmarX, which further facilitates the seamless integration and interchange of third-party contributions. To showcase the robot's capabilities, we present its performance in a challenging industrial maintenance scenario that requires human-robot collaboration, where the robot autonomously recognizes the human's need of help and offers said help in a proactive way.
- 30 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 26 (4) , 108-121
Open AccessARMAR-6: A High-Performance Humanoid for Human-Robot Collaboration in Real-World Scenarios
A major goal of humanoid robotics is to enable safe and reliable human-robot collaboration in realworld scenarios. In this article, we present ARMAR-6, a new high-performance humanoid robot for various tasks, including but not limited to grasping, mobile manipulation, integrated perception, bimanual collaboration, compliant-motion execution, and natural language understanding. We describe how the requirements arising from these tasks influenced our major design decisions, resulting in vertical integration during the joint hardware and software development phases. In particular, the entire hardware-including its structure, sensor-actuator units, and low-level controllers-as well as its perception, grasping and manipulation skills, task coordination, and the entire software architecture were all developed by one team of engineers. Component interaction is facilitated by our software framework ArmarX, which further facilitates the seamless integration and interchange of third-party contributions. To showcase the robot's capabilities, we present its performance in a challenging industrial maintenance scenario that requires human-robot collaboration, where the robot autonomously recognizes the human's need of help and offers said help in a proactive way.
- 26 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 3 (4) , 4007-4014
Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory that facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model as follows: First, encodes observed actions in a latent vector space and, based on this latent encoding, second, infers most similar episodes previously experienced, third, reconstructs original episodes, and finally, predicts future frames in an end-to-end fashion. Results show that conceptually similar actions are mapped into the same region of the latent vector space. Based on these results, we introduce an action matching and retrieval mechanism, benchmark its performance on two large-scale action datasets, 20BN-something-something and ActivityNet and evaluate its generalization capability in a real-world scenario on a humanoid robot.
- 26 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 3 (4) , 4007-4014
Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory that facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model as follows: First, encodes observed actions in a latent vector space and, based on this latent encoding, second, infers most similar episodes previously experienced, third, reconstructs original episodes, and finally, predicts future frames in an end-to-end fashion. Results show that conceptually similar actions are mapped into the same region of the latent vector space. Based on these results, we introduce an action matching and retrieval mechanism, benchmark its performance on two large-scale action datasets, 20BN-something-something and ActivityNet and evaluate its generalization capability in a real-world scenario on a humanoid robot.
- 31 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 3 (3) , 1410-1417
Vision-Based Online Adaptation of Motion Primitives to Dynamic Surfaces: Application to an Interactive Robotic Wiping Task
Elderly or disabled people usually need augmented nursing attention both in home and clinical environments, especially to perform bathing activities. The development of an assistive robotic bath system, which constitutes a central motivation of this letter, would increase the independence and safety of this procedure, ameliorating in this way the everyday life for this group of people. In general terms, the main goal of this letter is to enable natural, physical human-robot interaction, involving human-friendly and user-adaptive online robot motion planning and interaction control. For this purpose, we employ imitation learning using a leader-follower framework called coordinate change dynamic movement primitives (CC-DMP), in order to incorporate the expertise of professional carers for bathing sequences. In this letter, we propose a vision-based washing system, combining CC-DMP framework with a perception-based controller, to adapt the motion of robot's end effector on moving and deformable surfaces, such as a human body part. The controller guarantees globally uniformly asymptotic convergence to the leader movement primitive while ensuring avoidance of restricted areas, such as sensitive skin body areas. We experimentally tested our approach on a setup including the humanoid robot ARMAR-III and a Kinect v2 camera. The robot executes motions learned from the publicly available KIT whole-body human motion database, achieving good tracking performance in challenging interactive task scenarios.
- 31 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 3 (3) , 1410-1417
Vision-Based Online Adaptation of Motion Primitives to Dynamic Surfaces: Application to an Interactive Robotic Wiping Task
Elderly or disabled people usually need augmented nursing attention both in home and clinical environments, especially to perform bathing activities. The development of an assistive robotic bath system, which constitutes a central motivation of this letter, would increase the independence and safety of this procedure, ameliorating in this way the everyday life for this group of people. In general terms, the main goal of this letter is to enable natural, physical human-robot interaction, involving human-friendly and user-adaptive online robot motion planning and interaction control. For this purpose, we employ imitation learning using a leader-follower framework called coordinate change dynamic movement primitives (CC-DMP), in order to incorporate the expertise of professional carers for bathing sequences. In this letter, we propose a vision-based washing system, combining CC-DMP framework with a perception-based controller, to adapt the motion of robot's end effector on moving and deformable surfaces, such as a human body part. The controller guarantees globally uniformly asymptotic convergence to the leader movement primitive while ensuring avoidance of restricted areas, such as sensitive skin body areas. We experimentally tested our approach on a setup including the humanoid robot ARMAR-III and a Kinect v2 camera. The robot executes motions learned from the publicly available KIT whole-body human motion database, achieving good tracking performance in challenging interactive task scenarios.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 109-116
Enriched manipulation action semantics for robot execution of time constrained tasks
This paper contributes to semantic representation of human demonstrated actions for robot execution of time constrained tasks. We propose a semantic action encoding method based on interactions between the subject and objects in the scene. Our semantic framework is enriched with a descriptive spatial reasoning method which leads to accurate segmentation and recognition of unique action primitives. The proposed framework can classify the segmented action primitives as periodic or discrete to allow robots to autonomously decide how to imitate observed actions at different temporal scales. We evaluated our framework on our new large manipulation action dataset which involves in total 70 demonstrations from 8 different action types. We conducted various experiments with our humanoid robot to evaluate the proposed framework.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 109-116
Enriched manipulation action semantics for robot execution of time constrained tasks
This paper contributes to semantic representation of human demonstrated actions for robot execution of time constrained tasks. We propose a semantic action encoding method based on interactions between the subject and objects in the scene. Our semantic framework is enriched with a descriptive spatial reasoning method which leads to accurate segmentation and recognition of unique action primitives. The proposed framework can classify the segmented action primitives as periodic or discrete to allow robots to autonomously decide how to imitate observed actions at different temporal scales. We evaluated our framework on our new large manipulation action dataset which involves in total 70 demonstrations from 8 different action types. We conducted various experiments with our humanoid robot to evaluate the proposed framework.
- 1 March 2016
- Published by Springer Nature in Journal of Thermal Analysis and Calorimetry
- Vol. 125 (1) , 245-254
Smoke and toxicity suppression properties of ferrites on flame-retardant polyurethane–polyisocyanurate foams filled with phosphonate
- 1 March 2016
- Published by Springer Nature in Journal of Thermal Analysis and Calorimetry
- Vol. 125 (1) , 245-254
Smoke and toxicity suppression properties of ferrites on flame-retardant polyurethane–polyisocyanurate foams filled with phosphonate