Pub Date : 2024-04-04DOI: 10.1109/TCDS.2024.3373155
{"title":"IEEE Transactions on Cognitive and Developmental Systems Information for Authors","authors":"","doi":"10.1109/TCDS.2024.3373155","DOIUrl":"https://doi.org/10.1109/TCDS.2024.3373155","url":null,"abstract":"","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 2","pages":"C4-C4"},"PeriodicalIF":5.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10491285","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140348385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The fully supervised semantic segmentation requires detailed annotation of each pixel, which is time-consuming and laborious at the pixel-by-pixel level. To solve this problem, the direction of this article is to perform the semantic segmentation task by using image-level categorical annotation. Existing methods using image level annotation usually use class activation maps (CAMs) to find the location of the target object as the first step. By training a classifier, the presence of objects in the image can be searched effectively. However, CAMs appear that as follows: 1) objects are excessively focused on specific regions, capturing only the most prominent and critical areas and 2) it is easy to misinterpret the frequently occurring background regions, the foreground and background are confused. This article introduces cross language image matching based on out-of-distribution data and convolutional block attention module (CLODA), the concept of double branching in the cross language image matching framework, and adds a convolutional attention module to the attention branch to solve the problem of excess focus on objects in the CAMs. Importing out-of-distribution data on out of distribution branches helps classification networks improve misinterpretation of areas of focus. Optimizing regions of interest for attentional branch learning using cross pseudosupervision on two branches. Experimental results show that the pseudomasks generated by the proposed network can achieve 75.3% in mean Intersection over Union (mIoU) with the pattern analysis, statistical modeling and computational learning visual object classes (PASCAL VOC) 2012 training set. The performance of the segmentation network trained with the pseudomasks is up to 72.3% and 72.1% in mIoU on the validation and testing set of PASCAL VOC 2012.
{"title":"Attention Mechanism and Out-of-Distribution Data on Cross Language Image Matching for Weakly Supervised Semantic Segmentation","authors":"Chi-Chia Sun;Jing-Ming Guo;Chen-Hung Chung;Bo-Yu Chen","doi":"10.1109/TCDS.2024.3382914","DOIUrl":"10.1109/TCDS.2024.3382914","url":null,"abstract":"The fully supervised semantic segmentation requires detailed annotation of each pixel, which is time-consuming and laborious at the pixel-by-pixel level. To solve this problem, the direction of this article is to perform the semantic segmentation task by using image-level categorical annotation. Existing methods using image level annotation usually use class activation maps (CAMs) to find the location of the target object as the first step. By training a classifier, the presence of objects in the image can be searched effectively. However, CAMs appear that as follows: 1) objects are excessively focused on specific regions, capturing only the most prominent and critical areas and 2) it is easy to misinterpret the frequently occurring background regions, the foreground and background are confused. This article introduces cross language image matching based on out-of-distribution data and convolutional block attention module (CLODA), the concept of double branching in the cross language image matching framework, and adds a convolutional attention module to the attention branch to solve the problem of excess focus on objects in the CAMs. Importing out-of-distribution data on out of distribution branches helps classification networks improve misinterpretation of areas of focus. Optimizing regions of interest for attentional branch learning using cross pseudosupervision on two branches. Experimental results show that the pseudomasks generated by the proposed network can achieve 75.3% in mean Intersection over Union (mIoU) with the pattern analysis, statistical modeling and computational learning visual object classes (PASCAL VOC) 2012 training set. The performance of the segmentation network trained with the pseudomasks is up to 72.3% and 72.1% in mIoU on the validation and testing set of PASCAL VOC 2012.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 4","pages":"1604-1610"},"PeriodicalIF":5.0,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140593955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-02DOI: 10.1109/TCDS.2024.3383952
Sonal Kumar;Arijit Sur;Rashmi Dutta Baruah
Successive proposals of several self-supervised training schemes (STSs) continue to emerge, taking one step closer to developing a universal foundation model. In this process, unsupervised downstream tasks are recognized as one of the evaluation methods to validate the quality of visual features learned with self-supervised training. However, unsupervised dense semantic segmentation has yet to be explored as a downstream task, which can utilize and evaluate the quality of semantic information introduced in patch-level feature representations during self-supervised training of vision transformers. Therefore, we propose a novel data-driven framework, DatUS, to perform unsupervised dense semantic segmentation (DSS) as a downstream task. DatUS generates semantically consistent pseudosegmentation masks for an unlabeled image dataset without using visual prior or synchronized data. The experiment shows that the proposed framework achieves the highest MIoU (24.90) and average F1 score (36.3) by choosing DINOv2 and the highest pixel accuracy (62.18) by choosing DINO as the STS on the training set of SUIM dataset. It also outperforms state-of-the-art methods for the unsupervised DSS task with 15.02% MIoU, 21.47% pixel accuracy, and 16.06% average F1 score on the validation set of SUIM dataset. It achieves a competitive level of accuracy for a large-scale COCO dataset.
{"title":"DatUS: Data-Driven Unsupervised Semantic Segmentation With Pretrained Self-Supervised Vision Transformer","authors":"Sonal Kumar;Arijit Sur;Rashmi Dutta Baruah","doi":"10.1109/TCDS.2024.3383952","DOIUrl":"10.1109/TCDS.2024.3383952","url":null,"abstract":"Successive proposals of several self-supervised training schemes (STSs) continue to emerge, taking one step closer to developing a universal foundation model. In this process, unsupervised downstream tasks are recognized as one of the evaluation methods to validate the quality of visual features learned with self-supervised training. However, unsupervised dense semantic segmentation has yet to be explored as a downstream task, which can utilize and evaluate the quality of semantic information introduced in patch-level feature representations during self-supervised training of vision transformers. Therefore, we propose a novel data-driven framework, DatUS, to perform unsupervised dense semantic segmentation (DSS) as a downstream task. DatUS generates semantically consistent pseudosegmentation masks for an unlabeled image dataset without using visual prior or synchronized data. The experiment shows that the proposed framework achieves the highest MIoU (24.90) and average F1 score (36.3) by choosing DINOv2 and the highest pixel accuracy (62.18) by choosing DINO as the STS on the training set of SUIM dataset. It also outperforms state-of-the-art methods for the unsupervised DSS task with 15.02% MIoU, 21.47% pixel accuracy, and 16.06% average F1 score on the validation set of SUIM dataset. It achieves a competitive level of accuracy for a large-scale COCO dataset.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 5","pages":"1775-1788"},"PeriodicalIF":5.0,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140593839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-02DOI: 10.1109/TCDS.2024.3384269
Yuqi Liu;Qichao Zhang;Yinfeng Gao;Dongbin Zhao
Learning an efficient and safe driving strategy in a traffic-heavy intersection scenario and generalizing it to different intersections remains a challenging task for autonomous driving. This is because there are differences in the structure of roads at different intersections, and autonomous vehicles need to generalize the strategies they have learned in the training environments. This requires the autonomous vehicle to capture not only the interactions between agents but also the relationships between agents and the map effectively. To address this challenge, we present a technique that integrates the information of high-definition (HD) maps and traffic participants into vector representations, called lane graph vectorization (LGV). In order to construct a driving policy for intersection navigation, we incorporate LGV into the twin-delayed deep deterministic policy gradient (TD3) algorithm with prioritized experience replay (PER). To train and validate the proposed algorithm, we construct a gym environment for intersection navigation within the high-fidelity CARLA simulator, integrating dense interactive traffic flow and various generalization test intersection scenarios. Experimental results demonstrate the effectiveness of LGV for intersection navigation tasks and outperform the state-of-the-art in our proposed scenarios.
{"title":"Deep-Reinforcement-Learning-Based Driving Policy at Intersections Utilizing Lane Graph Networks","authors":"Yuqi Liu;Qichao Zhang;Yinfeng Gao;Dongbin Zhao","doi":"10.1109/TCDS.2024.3384269","DOIUrl":"10.1109/TCDS.2024.3384269","url":null,"abstract":"Learning an efficient and safe driving strategy in a traffic-heavy intersection scenario and generalizing it to different intersections remains a challenging task for autonomous driving. This is because there are differences in the structure of roads at different intersections, and autonomous vehicles need to generalize the strategies they have learned in the training environments. This requires the autonomous vehicle to capture not only the interactions between agents but also the relationships between agents and the map effectively. To address this challenge, we present a technique that integrates the information of high-definition (HD) maps and traffic participants into vector representations, called lane graph vectorization (LGV). In order to construct a driving policy for intersection navigation, we incorporate LGV into the twin-delayed deep deterministic policy gradient (TD3) algorithm with prioritized experience replay (PER). To train and validate the proposed algorithm, we construct a gym environment for intersection navigation within the high-fidelity CARLA simulator, integrating dense interactive traffic flow and various generalization test intersection scenarios. Experimental results demonstrate the effectiveness of LGV for intersection navigation tasks and outperform the state-of-the-art in our proposed scenarios.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 5","pages":"1759-1774"},"PeriodicalIF":5.0,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140594174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-01DOI: 10.1109/TCDS.2024.3383428
Yangfan Hu;Qian Zheng;Gang Pan
To address the energy bottleneck in deep neural networks (DNNs), the research community has developed binary neural networks (BNNs) and spiking neural networks (SNNs) from different perspectives. To combine the advantages of both BNNs and SNNs for better energy efficiency, this article proposes BitSNNs, which leverage binary weights, single-step inference, and activation sparsity. During the development of BitSNNs, we observed performance degradation in deep ResNets due to the gradient approximation error. To mitigate this issue, we delve into the learning process and propose the utilization of a hardtanh function before activation binarization. Additionally, this article investigates the critical role of activation sparsity in BitSNNs for energy efficiency, a topic often overlooked in the existing literature. Our study reveals strategies to strike a balance between accuracy and energy consumption during the training/testing stage, potentially benefiting applications in edge computing. Notably, our proposed method achieves state-of-the-art performance while significantly reducing energy consumption.
{"title":"BitSNNs: Revisiting Energy-Efficient Spiking Neural Networks","authors":"Yangfan Hu;Qian Zheng;Gang Pan","doi":"10.1109/TCDS.2024.3383428","DOIUrl":"10.1109/TCDS.2024.3383428","url":null,"abstract":"To address the energy bottleneck in deep neural networks (DNNs), the research community has developed binary neural networks (BNNs) and spiking neural networks (SNNs) from different perspectives. To combine the advantages of both BNNs and SNNs for better energy efficiency, this article proposes BitSNNs, which leverage binary weights, single-step inference, and activation sparsity. During the development of BitSNNs, we observed performance degradation in deep ResNets due to the gradient approximation error. To mitigate this issue, we delve into the learning process and propose the utilization of a hardtanh function before activation binarization. Additionally, this article investigates the critical role of activation sparsity in BitSNNs for energy efficiency, a topic often overlooked in the existing literature. Our study reveals strategies to strike a balance between accuracy and energy consumption during the training/testing stage, potentially benefiting applications in edge computing. Notably, our proposed method achieves state-of-the-art performance while significantly reducing energy consumption.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 5","pages":"1736-1747"},"PeriodicalIF":5.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140593968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-01DOI: 10.1109/TCDS.2024.3383158
Boyu Li;Haoran Li;Yuanheng Zhu;Dongbin Zhao
Agent-agnostic reinforcement learning aims to learn a universal control policy that can simultaneously control a set of robots with different morphologies. Recent studies have suggested that using the transformer model can address variations in state and action spaces caused by different morphologies, and morphology information is necessary to improve policy performance. However, existing methods have limitations in exploiting morphological information, where the rationality of observation integration cannot be guaranteed. We propose morphological adaptive transformer (MAT), a transformer-based universal control algorithm that can adapt to various morphologies without any modifications. MAT includes two essential components: functional position encoding (FPE) and morphological attention mechanism (MAM). The FPE provides robust and consistent positional prior information for limb observation to avoid limb confusion and implicitly obtain functional descriptions of limbs. The MAM enhances the attribute prior information of limbs, improves the correlation between observations, and makes the policy pay attention to more limbs. We combine observation with prior information to help policy adapt to the morphology of robots, thereby optimizing its performance with unknown morphologies. Experiments on agent-agnostic tasks in Gym MuJoCo environment demonstrate that our algorithm can assign more reasonable morphological prior information to each limb, and the performance of our algorithm is comparable to the prior state-of-the-art algorithm with better generalization.
{"title":"MAT: Morphological Adaptive Transformer for Universal Morphology Policy Learning","authors":"Boyu Li;Haoran Li;Yuanheng Zhu;Dongbin Zhao","doi":"10.1109/TCDS.2024.3383158","DOIUrl":"10.1109/TCDS.2024.3383158","url":null,"abstract":"Agent-agnostic reinforcement learning aims to learn a universal control policy that can simultaneously control a set of robots with different morphologies. Recent studies have suggested that using the transformer model can address variations in state and action spaces caused by different morphologies, and morphology information is necessary to improve policy performance. However, existing methods have limitations in exploiting morphological information, where the rationality of observation integration cannot be guaranteed. We propose morphological adaptive transformer (MAT), a transformer-based universal control algorithm that can adapt to various morphologies without any modifications. MAT includes two essential components: functional position encoding (FPE) and morphological attention mechanism (MAM). The FPE provides robust and consistent positional prior information for limb observation to avoid limb confusion and implicitly obtain functional descriptions of limbs. The MAM enhances the attribute prior information of limbs, improves the correlation between observations, and makes the policy pay attention to more limbs. We combine observation with prior information to help policy adapt to the morphology of robots, thereby optimizing its performance with unknown morphologies. Experiments on agent-agnostic tasks in Gym MuJoCo environment demonstrate that our algorithm can assign more reasonable morphological prior information to each limb, and the performance of our algorithm is comparable to the prior state-of-the-art algorithm with better generalization.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 4","pages":"1611-1621"},"PeriodicalIF":5.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140593972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-30DOI: 10.1109/TCDS.2024.3405573
Dhruv Sharma;Chhavi Dhiman;Dinesh Kumar
Automatic image captioning is a computationally intensive and structurally complicated task that describes the contents of an image in the form of a natural language sentence. Methods developed in the recent past focused mainly on the description of factual content in images thereby ignoring the different emotions and styles (romantic, humorous, angry, etc.) associated with the image. To overcome this, few works incorporated style-based caption generation that captures the variability in the generated descriptions. This article presents a style embedding-based variational autoencoder for controlled stylized caption generation framework (RFCG+SE-VAE-CSCG). It generates controlled text-based stylized descriptions of images. It works in two phases, i.e., $ 1)$ refined factual caption generation (RFCG); and $ 2)$ SE-VAE-CSCG. The former defines an encoder–decoder model for the generation of refined factual captions. Whereas, the latter presents a SE-VAE for controlled stylized caption generation. The overall proposed framework generates style-based descriptions of images by leveraging bag of captions (BoCs). More so, with the use of a controlled text generation model, the proposed work efficiently learns disentangled representations and generates realistic stylized descriptions of images. Experiments on MSCOCO, Flickr30K, and FlickrStyle10K provide state-of-the-art results for both refined and style-based caption generation, supported with an ablation study.
{"title":"Control With Style: Style Embedding-Based Variational Autoencoder for Controlled Stylized Caption Generation Framework","authors":"Dhruv Sharma;Chhavi Dhiman;Dinesh Kumar","doi":"10.1109/TCDS.2024.3405573","DOIUrl":"10.1109/TCDS.2024.3405573","url":null,"abstract":"Automatic image captioning is a computationally intensive and structurally complicated task that describes the contents of an image in the form of a natural language sentence. Methods developed in the recent past focused mainly on the description of factual content in images thereby ignoring the different emotions and styles (romantic, humorous, angry, etc.) associated with the image. To overcome this, few works incorporated style-based caption generation that captures the variability in the generated descriptions. This article presents a style embedding-based variational autoencoder for controlled stylized caption generation framework (RFCG+SE-VAE-CSCG). It generates controlled text-based stylized descriptions of images. It works in two phases, i.e., \u0000<inline-formula><tex-math>$ 1)$</tex-math></inline-formula>\u0000 refined factual caption generation (RFCG); and \u0000<inline-formula><tex-math>$ 2)$</tex-math></inline-formula>\u0000 SE-VAE-CSCG. The former defines an encoder–decoder model for the generation of refined factual captions. Whereas, the latter presents a SE-VAE for controlled stylized caption generation. The overall proposed framework generates style-based descriptions of images by leveraging bag of captions (BoCs). More so, with the use of a controlled text generation model, the proposed work efficiently learns disentangled representations and generates realistic stylized descriptions of images. Experiments on MSCOCO, Flickr30K, and FlickrStyle10K provide state-of-the-art results for both refined and style-based caption generation, supported with an ablation study.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 6","pages":"2032-2042"},"PeriodicalIF":5.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141195536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-30DOI: 10.1109/TCDS.2024.3405896
Xiaohan Huang;Yuhu Cheng;Qiang Yu;Xuesong Wang
In the field of autonomous driving, safety has always been a top priority, especially in recent years with the development and increasing application of deep reinforcement learning (DRL) in autonomous driving. Ensuring the safety of algorithms has become an indispensable concern. Reinforcement learning (RL), which involves interacting with the environment through trial and error, may result in unsafe behavior in autonomous driving without any safety constraints. Such behavior could result in the drive path deviation and even collision, causing catastrophic accidents. Therefore, this article proposes a reinforcement learning algorithm based on a safety experience replay mechanism, which is primarily to enhance the safety of reinforcement learning in autonomous driving. First, the ego vehicle conducts preliminary exploration of the environment to collect data. Based on the performance of completing tasks observed from each data trajectory, safety labels of different levels are assigned to all state-action pairs, which establishes a safety experience buffer. Further, a safety-critic network is constructed, which is trained by randomly sampling from the safety experience buffer. This enables the network to quantitatively evaluate the safety of driving actions, and the goal of safe driving for ego vehicle is achieved. The experimental results indicate that the proposed method can effectively reduce driving risks and improve task success rates compared with conventional reinforcement learning algorithms.
{"title":"Deep Reinforcement Learning for Autonomous Driving Based on Safety Experience Replay","authors":"Xiaohan Huang;Yuhu Cheng;Qiang Yu;Xuesong Wang","doi":"10.1109/TCDS.2024.3405896","DOIUrl":"10.1109/TCDS.2024.3405896","url":null,"abstract":"In the field of autonomous driving, safety has always been a top priority, especially in recent years with the development and increasing application of deep reinforcement learning (DRL) in autonomous driving. Ensuring the safety of algorithms has become an indispensable concern. Reinforcement learning (RL), which involves interacting with the environment through trial and error, may result in unsafe behavior in autonomous driving without any safety constraints. Such behavior could result in the drive path deviation and even collision, causing catastrophic accidents. Therefore, this article proposes a reinforcement learning algorithm based on a safety experience replay mechanism, which is primarily to enhance the safety of reinforcement learning in autonomous driving. First, the ego vehicle conducts preliminary exploration of the environment to collect data. Based on the performance of completing tasks observed from each data trajectory, safety labels of different levels are assigned to all state-action pairs, which establishes a safety experience buffer. Further, a safety-critic network is constructed, which is trained by randomly sampling from the safety experience buffer. This enables the network to quantitatively evaluate the safety of driving actions, and the goal of safe driving for ego vehicle is achieved. The experimental results indicate that the proposed method can effectively reduce driving risks and improve task success rates compared with conventional reinforcement learning algorithms.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 6","pages":"2070-2084"},"PeriodicalIF":5.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141195749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.1109/TCDS.2024.3406730
Yongkang Luo;Wanyi Li;Peng Wang;Haonan Duan;Wei Wei;Jia Sun
Dexterous in-hand manipulation poses significant challenges for a multifingered anthropomorphic hand due to the high-dimensional state and action spaces, as well as the intricate contact patterns between the fingers and objects. Although deep reinforcement learning has made moderate progress and demonstrated its strong potential for manipulation, it faces certain challenges, including large-scale data collection and high sample complexity. Particularly in scenes with slight changes, it necessitates the recollection of vast amounts of data and numerous iterations of fine-tuning. Remarkably, humans can quickly transfer their learned manipulation skills to different scenarios with minimal supervision. Inspired by the flexible transfer learning capability of humans, we propose a novel framework called progressive transfer learning (PTL) for dexterous in-hand manipulation. This framework efficiently utilizes the collected trajectories and the dynamics model trained on a source dataset. It adopts progressive neural networks for dynamics model transfer learning on samples selected using a new method based on dynamics properties, rewards, and trajectory scores. Experimental results on contact-rich anthropomorphic hand manipulation tasks demonstrate that our method can efficiently and effectively learn in-hand manipulation skills with just a few online attempts and adjustment learning in the new scene. Moreover, compared to learning from scratch, our method significantly reduces training time costs by 85%.
{"title":"Progressive Transfer Learning for Dexterous In-Hand Manipulation With Multifingered Anthropomorphic Hand","authors":"Yongkang Luo;Wanyi Li;Peng Wang;Haonan Duan;Wei Wei;Jia Sun","doi":"10.1109/TCDS.2024.3406730","DOIUrl":"10.1109/TCDS.2024.3406730","url":null,"abstract":"Dexterous in-hand manipulation poses significant challenges for a multifingered anthropomorphic hand due to the high-dimensional state and action spaces, as well as the intricate contact patterns between the fingers and objects. Although deep reinforcement learning has made moderate progress and demonstrated its strong potential for manipulation, it faces certain challenges, including large-scale data collection and high sample complexity. Particularly in scenes with slight changes, it necessitates the recollection of vast amounts of data and numerous iterations of fine-tuning. Remarkably, humans can quickly transfer their learned manipulation skills to different scenarios with minimal supervision. Inspired by the flexible transfer learning capability of humans, we propose a novel framework called progressive transfer learning (PTL) for dexterous in-hand manipulation. This framework efficiently utilizes the collected trajectories and the dynamics model trained on a source dataset. It adopts progressive neural networks for dynamics model transfer learning on samples selected using a new method based on dynamics properties, rewards, and trajectory scores. Experimental results on contact-rich anthropomorphic hand manipulation tasks demonstrate that our method can efficiently and effectively learn in-hand manipulation skills with just a few online attempts and adjustment learning in the new scene. Moreover, compared to learning from scratch, our method significantly reduces training time costs by 85%.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 6","pages":"2019-2031"},"PeriodicalIF":5.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141195537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.1109/TCDS.2024.3383296
Yuchen Yan;Haotian Su;Yunyi Jia
The development of collaborative robots has enabled a safer and more efficient human–robot collaboration (HRC) manufacturing environment. Tremendous research efforts have been conducted to improve user safety and robot working efficiency after the debut of collaborative robots. However, human comfort in HRC scenarios has not been thoroughly discussed but is critically important to the user acceptance of collaborative robots. Previous studies mostly utilize the subjective rating method to evaluate how human comfort varies as one robot factor changes, yet such method is limited in evaluating comfort online. Some other studies leverage wearable sensors to collect physiological signals to detect human emotions, but few of them implement this for a human comfort model in HRC scenarios. In this study, we designed an online comfort model for HRC using wearable sensing data. The model uses physiological signals acquired from wearable sensing and calculates the in-situ human comfort levels based on our developed algorithms. We have conducted experiments in realistic HRC tasks, and the prediction results demonstrated the effectiveness of the proposed approach in identifying human comfort levels in HRC.
{"title":"Measuring Human Comfort in Human–Robot Collaboration via Wearable Sensing","authors":"Yuchen Yan;Haotian Su;Yunyi Jia","doi":"10.1109/TCDS.2024.3383296","DOIUrl":"10.1109/TCDS.2024.3383296","url":null,"abstract":"The development of collaborative robots has enabled a safer and more efficient human–robot collaboration (HRC) manufacturing environment. Tremendous research efforts have been conducted to improve user safety and robot working efficiency after the debut of collaborative robots. However, human comfort in HRC scenarios has not been thoroughly discussed but is critically important to the user acceptance of collaborative robots. Previous studies mostly utilize the subjective rating method to evaluate how human comfort varies as one robot factor changes, yet such method is limited in evaluating comfort online. Some other studies leverage wearable sensors to collect physiological signals to detect human emotions, but few of them implement this for a human comfort model in HRC scenarios. In this study, we designed an online comfort model for HRC using wearable sensing data. The model uses physiological signals acquired from wearable sensing and calculates the in-situ human comfort levels based on our developed algorithms. We have conducted experiments in realistic HRC tasks, and the prediction results demonstrated the effectiveness of the proposed approach in identifying human comfort levels in HRC.","PeriodicalId":54300,"journal":{"name":"IEEE Transactions on Cognitive and Developmental Systems","volume":"16 5","pages":"1748-1758"},"PeriodicalIF":5.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140594186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：