检索结果-内蒙古大学图书馆

Domain generalization for vision-based driving trajectory generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yunkai Zhang, Dongkun Cui, Yuxiang Chen, Zexi Jing, Wei Chen, Junbo Xiong, Rong Wang, Yue State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Autonomous Driving Lab Alibaba DAMO Academy Hangzhou China

One of the challenges in vision-based driving trajectory generation is dealing with out-of-distribution scenarios. In this paper, we propose a domain generalization method for vision-based driving trajectory generation for autonomous vehicles in urban environments, which can be seen as a solution to extend the Invariant Risk Minimization (IRM) method in complex problems. We leverage an adversarial learning approach to train a trajectory generator as the decoder. Based on the pre-trained decoder, we infer the latent variables corresponding to the trajectories, and pre-train the encoder by regressing the inferred latent variable. Finally, we fix the decoder but fine-tune the encoder with the final trajectory loss. We compare our proposed method with the state-of-the-art trajectory generation method and some recent domain generalization methods on both datasets and simulation, demonstrating that our method has better generalization ability. Our project is available at https://***/view/dg-traj-gen. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

Two-Timescale Nonlinear Model Predictive control for Flexible Operation of Coal-Fired Power Plant with Post Combustion Co 2 Capture System

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Yang, Chao Guo, Wenxuan Shao, Yuhao Lin, Yangshu Pu, Xuesen Wang, Yifan Zheng, Chenghang Ding, Yi Fan, Haidong Zhu, Yucai Gao, Xiang State Key Lab of Clean Energy Utilization State Environmental Protection Center for Coal-Fired Air Pollution Control Zhejiang University Hangzhou310027 China State Key Lab of Clean Energy Utilization Institute of Carbon Neutrality State Environmental Protection Engineering Center for Coal-Fired Air Pollution Control Zhejiang University Hangzhou310027 China Dongfang Electric Autocontrol Engineering Co. LTD. Deyang618000 China College of Electrical Engineering Zhejiang University Hangzhou310027 China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Post-combustion carbon capture (PCC) with chemical absorption exhibits significant interactions with coal-fired power plants (CFPP). The mismatch in the timescales of dynamic responses between PCC and CFPP, along with their nonlinear characteristics, presents additional challenges for the design of controllers. To address these obstacles, this work presents a two-timescale nonlinear model predictive control (T-NMPC) strategy to align the operational flexibility of the CFPP-PCC coupled system. A slow timescale nonlinear model predictive controller (S-NMPC) manages the extensive set of variables within the integrated CFPP-PCC system, focusing on long-term stability. In contrast, a fast timescale nonlinear model predictive controller (F-NMPC) dynamically adjusts the CFPP power and steam pressure to meet real-time operational demands. The interaction between these two controllers, both using extraction steam as a controlled variable, increases the flexibility of the CFPP by exploiting the energy buffers in the PCC. Comprehensive simulations of the CFPP-PCC system substantiate the enhancements in automatic generation control (AGC) performance, affirming the strategy's effectiveness. © 2024, The Authors. All rights reserved.

关键词： Coal fired power plant

Multi-chamber pneumatic actuator for peristaltic soft robot

学校读者我要写书评

暂无评论

Multi-chamber pneumatic actuator for peristaltic soft robot

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Gao, Sheng Wang, Yue Xiong, Rong Gong, Zhefeng Zheng, Nenggan Lu, Haojian Zhejiang University Department of Polytechnic Institute Hangzhou310058 China Key Laboratory of Medical Neurobiology of the Ministry of Health of China Key Laboratory of Neurobiology Zhejiang University School of Medicine Zhejiang Lab Department of Neurobiology Hangzhou310058 China Qiushi Academy for Advanced Studies Zhejiang University Zhejiang Provincial Key Laboratory of Cardio-Cerebral Vascular Detection Technology Hangzhou310058 China Institute of Cyber-Systems and Control Zhejiang University State Key Laboratory of Industrial Control and Technology Hangzhou China

ISBN: (纸本)9781665436786

Soft robots have the characteristics of high flexibility and strong environmental adaptability compared with traditional robots, and the peristaltic soft robot is a critical class for this field because of the peristaltic creature's superior softness, various movement, and can through complex space. However, this soft robot has the problem of single motion or limited deformation ability at present. In this paper, a pneumatic corrugated structure driver with a multi-chamber was designed to squirmy soft robots, it can elongation, contraction and turning. We designed the actuator's structure and fabrication of the model. Simultaneously, a set of controller systems is built to control its deformation, we complete the action of forwarding and turning with the actuator on experiments. © 2021 IEEE.

关键词： Pneumatic actuators

Schedule your edit: a simple yet effective diffusion noise schedule for image editing 24

学校读者我要写书评

暂无评论

Schedule your edit: a simple yet effective diffusion noise s...

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Haonan Lin Yan Chen Jiahao Wang Wenbin An Mengmeng Wang Feng Tian Yong Liu Guang Dai Jingdong Wang Qianying Wang School of Comp. Science & Technology MOEKLINNS Lab Xi'an Jiaotong University School of Auto. Science & Engineering MOEKLINNS Lab Xi'an Jiaotong University College of Comp. Science & Technology Zhejiang University of Technology and SGIT AI Lab State Grid Corporation of China Institute of Cyber-Systems and Control Zhejiang University and SGIT AI Lab State Grid Corporation of China SGIT AI Lab State Grid Corporation of China Baidu Inc Lenovo Research

ISBN: (纸本)9798331314385

Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. These errors accumulate during the diffusion process, resulting in inferior content preservation and edit fidelity, especially with conditional inputs. We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue. To resolve this, we introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. This schedule reduces noise prediction errors, enabling more faithful editing that preserves the original content of the source image. Our approach requires no additional retraining and is compatible with various existing editing methods. Experiments across eight editing tasks demonstrate the Logistic Schedule's superior performance in content preservation and edit fidelity compared to traditional noise schedules, highlighting its adaptability and effectiveness. (Project page: https://***/SYE/)

关键词：

Deep Domain Adaptation Regression for Force Calibration of Optical Tactile Sensors

学校读者我要写书评

暂无评论

Deep Domain Adaptation Regression for Force Calibration of O...

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Zhuo Chen Ni Ou Jiaqi Jiang Shan Luo Department of Engineering Robot Perception Lab Centre for Robotics Research King’s College London London United Kingdom State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4% in full force range) for normal force, and 0.095N (6.3%) and 0.062N (4.1%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors.

关键词： Accuracy Force Tactile sensors Lighting Elastomers Data collection Optical imaging Adaptive optics Calibration Optical sensors

Decentralized spatial-temporal trajectory planning for multicopter swarms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Xin Wang, Zhepei Wen, Xiangyong Zhu, Jiangchao Xu, Chao Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou313000 China

Multicopter swarms with decentralized structure possess the nature of flexibility and robustness, while efficient spatial-temporal trajectory planning still remains a challenge. This report introduces decentralized spatial-temporal trajectory planning, which puts a well-formed trajectory representation named MINCO into multi-agent scenarios. Our method ensures high-quality local planning for each agent subject to any constraint from either the coordination of the swarm or safety requirements in cluttered environments. Then, the local trajectory generation is formulated as an unconstrained optimization problem that is efficiently solved in milliseconds. Moreover, a decentralized asynchronous mechanism is designed to trigger the local planning for each agent. A systematic solution is presented with detailed descriptions of careful engineering considerations. Extensive benchmarks and indoor/outdoor experiments validate its wide applicability and high quality. Our software will be released for the reference of the community. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

Autonomous flights in dynamic environments with onboard vision

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yingjian Ji, Jialin Wang, Qianhao Xu, Chao Gao, Fei State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Huzhou Institute of Zhejiang University Huzhou313000 China

In this paper, we introduce a complete system for autonomous flight of quadrotors in dynamic environments with onboard sensing. Extended from existing work, we develop an occlusion-aware dynamic perception method based on depth images, which classifies obstacles as dynamic and static. For representing generic dynamic environment, we model dynamic objects with moving ellipsoids and fuse static ones into an occupancy grid map. To achieve dynamic avoidance, we design a planning method composed of modified kinodynamic path searching and gradient-based optimization. The method leverages manually constructed gradients without maintaining a signed distance field (SDF), making the planning procedure finished in milliseconds. We integrate the above methods into a customized quadrotor system and thoroughly test it in real-world experiments, verifying its effective collision avoidance in dynamic environments. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Distributed Swarm Trajectory Optimization for Formation Flight in Dense Environments

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Quan, Lun Yin, Longji Xu, Chao Gao, Fei The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China The Huzhou Institute Zhejiang University Huzhou313000 China

For aerial swarms, navigation in a prescribed formation is widely practiced in various scenarios. However, the associated planning strategies typically lack the capability of avoiding obstacles in cluttered environments. To address this deficiency, we present an optimization-based method that ensures collision-free trajectory generation for formation flight. In this paper, a novel differentiable metric is proposed to quantify the overall similarity distance between formations. We then formulate this metric into an optimization framework, which achieves spatial-temporal planning using polynomial trajectories. Minimization over collision penalty is also incorporated into the framework, so that formation preservation and obstacle avoidance can be handled simultaneously. To validate the efficiency of our method, we conduct benchmark comparisons with other cutting-edge works. Integrated with an autonomous distributed aerial swarm system, the proposed method demonstrates its efficiency and robustness in real-world experiments with obstacle-rich surroundings. We will release the source code for the reference of the community. Copyright © 2021, The Authors. All rights reserved.

关键词： Antennas

Photofabricated Channel-Digital Microfluidics (Pcdmf): A Promising lab-on-A-Chip Platform for Fully Integrated Digital Pcr

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： He, Yu Lu, Zefan Liu, Ke Wang, Lan Xu, Qiudi Fan, Hongliang Liu, Chong Zhang, Tao Research Center for Analytical Instrumentation Institute of Cyber-Systems and Control State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310023 China Huzhou Institute of Zhejiang University Huzhou313002 China School of Public Health Hangzhou Medical College Hangzhou311399 China Department of Neurobiology Department of Neurosurgery Second Affiliated Hospital School of Medicine Zhejiang University Hangzhou310023 China

Microfluidics-based digital PCR (dPCR) is a potent technique capable of absolute quantification of nucleic acids with ultrahigh sensitivity. However, an indispensable process, nucleic acid extraction (NAE) remains hard to be integrated with dPCR into a monolithic device, because both of them involve complicated processes and exquisite fluid manipulation. An ideal solution to this issue is to integrate the two main microfluidic platforms, channel-based microfluidics (CMF) and digital microfluidics (DMF), which, however, remains very challenging. To address these challenges, we herein develop a photofabricated channel-digital microfluidic chip (pCDMF) with significant advantages including: the fabrication of pCDMF is very convenient due to the flexible material choices of photocuring, without tedious process of hydrophobic coating;a parallel-plate configuration can be easily formed, enabling all basic functions of DMF;various channels and microstructures can be freely designed, allowing for fluidic functions of CMF. It is therefore the first example of full integration of DMF and CMF as a monolithic device, with capabilities to precisely handle both discrete droplets and continuous fluids. Finally, an all-in-one device for sample-to-answer digital PCR has been successfully demonstrated. We also envisioned that the pCDMF may open an alternative route toward the fully integrated lab-on-a-chip for various biological applications. © 2023, The Authors. All rights reserved.

关键词： Digital microfluidics