Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10355009
Umer Huzaifa, Dimuthu D. K. Arachchige, Muhammad Aneeq uz Zaman, Usman Syed
Soft robots have shown their value as alternatives or supplements to rigid robots in applications like search and rescue missions and complex precise tasks. Their ability to take on various shapes and apply adaptable force gives them an advantage over stiff robots. However, sometimes their soft structure doesn’t offer enough force for the task. Hybrid soft robots (HSRs) combine a soft body with a stronger backbone to handle tasks needing more strength. This rigid part lets us use rigid body dynamics to estimate HSR behavior. Here, we introduce a simplified N-link rigid body dynamic model with constant stiffness to mimic HSR behavior. While soft robots’ stiffness varies, the backbone in HSRs makes it similar to having constant stiffness. Comparing experiments supports the effectiveness of our N-link model for HSR modeling.
在搜救任务和复杂精密任务等应用中，软体机器人已显示出其作为刚性机器人替代品或补充的价值。与刚性机器人相比，软体机器人能够呈现出各种形状，并能施加适应性强的力，这使它们更具优势。然而，有时它们的软结构并不能为任务提供足够的力。混合软体机器人（HSR）结合了软体和更坚固的骨架，以处理需要更多力量的任务。我们可以利用刚体动力学来估计混合软体机器人的行为。在这里，我们引入了一个简化的具有恒定刚度的 N 连杆刚体动力学模型来模拟 HSR 的行为。软体机器人的刚度是变化的，而 HSR 中的骨架使其类似于具有恒定刚度。对比实验证明了我们的 N-连杆模型在 HSR 建模中的有效性。
{"title":"Simplified Modeling of Hybrid Soft Robots with Constant Stiffness Assumption","authors":"Umer Huzaifa, Dimuthu D. K. Arachchige, Muhammad Aneeq uz Zaman, Usman Syed","doi":"10.1109/ROBIO58561.2023.10355009","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10355009","url":null,"abstract":"Soft robots have shown their value as alternatives or supplements to rigid robots in applications like search and rescue missions and complex precise tasks. Their ability to take on various shapes and apply adaptable force gives them an advantage over stiff robots. However, sometimes their soft structure doesn’t offer enough force for the task. Hybrid soft robots (HSRs) combine a soft body with a stronger backbone to handle tasks needing more strength. This rigid part lets us use rigid body dynamics to estimate HSR behavior. Here, we introduce a simplified N-link rigid body dynamic model with constant stiffness to mimic HSR behavior. While soft robots’ stiffness varies, the backbone in HSRs makes it similar to having constant stiffness. Comparing experiments supports the effectiveness of our N-link model for HSR modeling.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"57 11","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Feature point extraction and matching is the key technology in object detection and simultaneous localization and mapping (SLAM). Aiming at the problems such as easy redundancy of feature points extracted by traditional ORB algorithm, low matching accuracy of mainstream robust estimation algorithms and low real-time performance, an improved ORB-GMS image feature extraction and matching algorithm is proposed. Firstly, the algorithm uses the gray value of the image to calculate the adaptive extraction threshold of the feature points. Then the image pyramid is constructed according to the image size. The set number of total feature points to be extracted is evenly distributed to each layer image according to the area ratio; Extract feature points from each layer of the image pyramid, and count the extracted feature points from each layer. If the number of feature points extracted from each layer meets the set number of images from each layer, the extraction ends. Then the quadtree algorithm is used to homogenize the feature points. Finally, the network scoring model is optimized from 8 neighborhood to 4 neighborhood, which reduces the computing time. Experimental results show that the matching accuracy of the proposed algorithm is 14% higher than that of the original algorithm, and the running time is 12% lower.
{"title":"An improved ORB-GMS image feature extraction and matching algorithm*","authors":"Zhiying Tan, Wenbo Fan, Weifeng Kong, Xu Tao, Linsen Xu, Xiaobin Xu","doi":"10.1109/ROBIO58561.2023.10355043","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10355043","url":null,"abstract":"Feature point extraction and matching is the key technology in object detection and simultaneous localization and mapping (SLAM). Aiming at the problems such as easy redundancy of feature points extracted by traditional ORB algorithm, low matching accuracy of mainstream robust estimation algorithms and low real-time performance, an improved ORB-GMS image feature extraction and matching algorithm is proposed. Firstly, the algorithm uses the gray value of the image to calculate the adaptive extraction threshold of the feature points. Then the image pyramid is constructed according to the image size. The set number of total feature points to be extracted is evenly distributed to each layer image according to the area ratio; Extract feature points from each layer of the image pyramid, and count the extracted feature points from each layer. If the number of feature points extracted from each layer meets the set number of images from each layer, the extraction ends. Then the quadtree algorithm is used to homogenize the feature points. Finally, the network scoring model is optimized from 8 neighborhood to 4 neighborhood, which reduces the computing time. Experimental results show that the matching accuracy of the proposed algorithm is 14% higher than that of the original algorithm, and the running time is 12% lower.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"78 4","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354764
Yusheng Yang, Jiajia Liu, Qiaoni Yang, Hang Shi, Yangmin Xie
With the advantages of high safety and scalability, collaborative robots are widely used in the fields of Human-Robot Collaboration and Interaction. However, the joint limits of the robot restrict its flexibility and workspace, especially in a cluttered environment. Inspired by the motion of the human arm, whose elbow joint and shoulder joint can rotate infinitely, a collaborative robot with the capability of infinite rotation of its first and fourth joints is constructed in this paper and named the IR-Robot. With the breakthrough of the joint limit, the corresponding dimension in the robot’s configuration space changes from a bounded dimension to an unbounded dimension. The high-dimensional torus configuration space (HTCS) is presented to describe the bounded-unbounded dimensions hybrid property of the IR-Robot’s configuration space. Additionally, an IR-RRT* algorithm is proposed to conduct path-planning in HTCS. The experimental results in simulation and the real world demonstrate the feasibility and superiority of the IR-Robot in path-following and path-planning tasks.
{"title":"Path-planning for the Human-arm-like Collaborative Robot with the Capability of Infinite Rotation","authors":"Yusheng Yang, Jiajia Liu, Qiaoni Yang, Hang Shi, Yangmin Xie","doi":"10.1109/ROBIO58561.2023.10354764","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354764","url":null,"abstract":"With the advantages of high safety and scalability, collaborative robots are widely used in the fields of Human-Robot Collaboration and Interaction. However, the joint limits of the robot restrict its flexibility and workspace, especially in a cluttered environment. Inspired by the motion of the human arm, whose elbow joint and shoulder joint can rotate infinitely, a collaborative robot with the capability of infinite rotation of its first and fourth joints is constructed in this paper and named the IR-Robot. With the breakthrough of the joint limit, the corresponding dimension in the robot’s configuration space changes from a bounded dimension to an unbounded dimension. The high-dimensional torus configuration space (HTCS) is presented to describe the bounded-unbounded dimensions hybrid property of the IR-Robot’s configuration space. Additionally, an IR-RRT* algorithm is proposed to conduct path-planning in HTCS. The experimental results in simulation and the real world demonstrate the feasibility and superiority of the IR-Robot in path-following and path-planning tasks.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"55 10","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354957
Yi Liu, Junyue Tang, Yafang Liu, Gongbo Ma, Feng Sun, Ye Li, Shengyuan Jiang
To exactly detect the water ice of the South Pole of the moon, a lunar regolith in-situ analysis payload deploying a mass spectrometer is proposed for China future lunar exploration missions. In order to receive the lunar regolith sample from a robotic arm with a soil sampler and transfer it into a furnace for further analysis, a sample manipulation mechanism is required during the above work flow. To solve the problems of adapting the sampler’s docking accuracy, receiving and transferring two different types of lunar soil sample under times of in-situ analysis, etc., a sample repetitive manipulation mechanism (SRMM) is proposed in this paper. By using a floating adjustable docking components and a flexible hopper, two types of encapsulated regolith sample and bulk material sample can be received with minimal sample loss, respectively. In order to receive and transfer two types of samples multiple times, two sample receiving methods have been designed that can be repeatedly transferred. A worm and worm wheel combined with a ball screw is designed in SRMM. To verify the above mechanism design, validation experiments were conducted. It indicates that this novel SRMM can be deployed in the future mission after further environmental tests.
{"title":"A Sample Repetitive Manipulation Mechanism (SRMM) for Lunar Regolith In-Situ Analysis: Design and Validation","authors":"Yi Liu, Junyue Tang, Yafang Liu, Gongbo Ma, Feng Sun, Ye Li, Shengyuan Jiang","doi":"10.1109/ROBIO58561.2023.10354957","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354957","url":null,"abstract":"To exactly detect the water ice of the South Pole of the moon, a lunar regolith in-situ analysis payload deploying a mass spectrometer is proposed for China future lunar exploration missions. In order to receive the lunar regolith sample from a robotic arm with a soil sampler and transfer it into a furnace for further analysis, a sample manipulation mechanism is required during the above work flow. To solve the problems of adapting the sampler’s docking accuracy, receiving and transferring two different types of lunar soil sample under times of in-situ analysis, etc., a sample repetitive manipulation mechanism (SRMM) is proposed in this paper. By using a floating adjustable docking components and a flexible hopper, two types of encapsulated regolith sample and bulk material sample can be received with minimal sample loss, respectively. In order to receive and transfer two types of samples multiple times, two sample receiving methods have been designed that can be repeatedly transferred. A worm and worm wheel combined with a ball screw is designed in SRMM. To verify the above mechanism design, validation experiments were conducted. It indicates that this novel SRMM can be deployed in the future mission after further environmental tests.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"41 5","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354986
Kohei Nishikawa, Y. Origane, Daisuke Kurabayashi
Modular robots are expected to be used in extreme environments owing to their adaptability, and various modular robots have been developed. Most studies have focused on the expandability of capabilities or the integration of modules, whereas only a few studies have investigated autonomous decentralized control, in which each module harmonizes its own movements for overall functionality. We developed an underwater modular robot that synchronizes its paddle strokes; the robot is based on the motif of Gonium, a multicellular alga. We built a reduced system model of modules to represent the state of an oscillator by using a phase with attractive interactions with others. Because the model is similar to the Kuramoto model, we applied analysis methods. Real robotic modules were built, and experiments were conducted using a colony of the modules. The experimental results confirmed that the colony exhibited stroke synchronization ability by compensating for individual differences. The stroke synchronization is expected to stabilize the movements of robot colonies and improve their overall propulsion.
{"title":"Stroke Synchronization of Underwater Modular Robot through Physical Interaction","authors":"Kohei Nishikawa, Y. Origane, Daisuke Kurabayashi","doi":"10.1109/ROBIO58561.2023.10354986","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354986","url":null,"abstract":"Modular robots are expected to be used in extreme environments owing to their adaptability, and various modular robots have been developed. Most studies have focused on the expandability of capabilities or the integration of modules, whereas only a few studies have investigated autonomous decentralized control, in which each module harmonizes its own movements for overall functionality. We developed an underwater modular robot that synchronizes its paddle strokes; the robot is based on the motif of Gonium, a multicellular alga. We built a reduced system model of modules to represent the state of an oscillator by using a phase with attractive interactions with others. Because the model is similar to the Kuramoto model, we applied analysis methods. Real robotic modules were built, and experiments were conducted using a colony of the modules. The experimental results confirmed that the colony exhibited stroke synchronization ability by compensating for individual differences. The stroke synchronization is expected to stabilize the movements of robot colonies and improve their overall propulsion.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"51 8","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10355037
Aryan Niknam Maleki, Alexander Thompson, M. Runciman, Julia Murray, G. Mylonas
Despite advances in radiotherapy, motion error remains a challenge in prostate radiotherapy. Rectal obturators and endorectal balloons may reduce motion error and improve outcomes but have limitations. We aimed to create a deployable rectal obturator with precise angle control to personalise to a patient’s rectal anatomy, by using an antagonistic pair of "muscle" actuators to flex and extend the device. Results on deployability, angle control, and radial stiffness are presented here. The device can be compressed down to 16 x 3 x 91 mm, and be deployed to maximum dimensions of 24 x 25.5 x 77 mm. The device provides radial stiffness that may be sufficient to stabilise the rectum during radiotherapy. Angle control can be achieved with an average change of 7.5°/ml inflation in the extensor actuator.
尽管放疗技术不断进步，但运动误差仍是前列腺放疗的一大难题。直肠闭塞器和肛门直肠内球囊可减少运动误差并改善治疗效果，但也有局限性。我们的目标是通过使用一对拮抗的 "肌肉 "致动器来弯曲和伸展装置，创造出一种具有精确角度控制功能的可展开直肠闭锁器，以便根据患者的直肠解剖结构进行个性化设计。本文介绍了该装置的可展开性、角度控制和径向刚度结果。该装置可压缩至 16 x 3 x 91 毫米，展开后的最大尺寸为 24 x 25.5 x 77 毫米。该装置提供的径向硬度足以在放疗期间稳定直肠。角度控制可通过伸展致动器 7.5°/ml 的平均充气变化来实现。
{"title":"A soft hydraulic endorectal actuator for prostate radiotherapy","authors":"Aryan Niknam Maleki, Alexander Thompson, M. Runciman, Julia Murray, G. Mylonas","doi":"10.1109/ROBIO58561.2023.10355037","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10355037","url":null,"abstract":"Despite advances in radiotherapy, motion error remains a challenge in prostate radiotherapy. Rectal obturators and endorectal balloons may reduce motion error and improve outcomes but have limitations. We aimed to create a deployable rectal obturator with precise angle control to personalise to a patient’s rectal anatomy, by using an antagonistic pair of \"muscle\" actuators to flex and extend the device. Results on deployability, angle control, and radial stiffness are presented here. The device can be compressed down to 16 x 3 x 91 mm, and be deployed to maximum dimensions of 24 x 25.5 x 77 mm. The device provides radial stiffness that may be sufficient to stabilise the rectum during radiotherapy. Angle control can be achieved with an average change of 7.5°/ml inflation in the extensor actuator.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"49 3","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper aims to explore the application of Bayesian deep reinforcement learning (BDRL) in robot manipulation tasks with sparse rewards, focusing on addressing the uncertainty in complex and sparsely rewarded environments. Conventional deep reinforcement learning (DRL) algorithms still face significant challenges in the context of robot manipulation tasks. To address this issue, this paper proposes a general algorithm framework called BDRL that combines reinforcement learning algorithms with Bayesian networks to quantify the model uncertainty, aleatoric uncertainty in neural networks, and uncertainty in the reward function. The effectiveness and generality of the proposed algorithm are validated through simulation experiments on multiple sets of different sparsely rewarded tasks, employing various advanced DRL algorithms. The research results demonstrate that the DRL algorithm based on the Bayesian network mechanism significantly improves the convergence speed of the algorithms in sparse reward tasks by accurately estimating the model uncertainty.
{"title":"Uncertainty in Bayesian Reinforcement Learning for Robot Manipulation Tasks with Sparse Rewards","authors":"Li Zheng, Yanghong Li, Yahao Wang, Guangrui Bai, Haiyang He, Erbao Dong","doi":"10.1109/ROBIO58561.2023.10354785","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354785","url":null,"abstract":"This paper aims to explore the application of Bayesian deep reinforcement learning (BDRL) in robot manipulation tasks with sparse rewards, focusing on addressing the uncertainty in complex and sparsely rewarded environments. Conventional deep reinforcement learning (DRL) algorithms still face significant challenges in the context of robot manipulation tasks. To address this issue, this paper proposes a general algorithm framework called BDRL that combines reinforcement learning algorithms with Bayesian networks to quantify the model uncertainty, aleatoric uncertainty in neural networks, and uncertainty in the reward function. The effectiveness and generality of the proposed algorithm are validated through simulation experiments on multiple sets of different sparsely rewarded tasks, employing various advanced DRL algorithms. The research results demonstrate that the DRL algorithm based on the Bayesian network mechanism significantly improves the convergence speed of the algorithms in sparse reward tasks by accurately estimating the model uncertainty.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"48 6","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354813
Gunjan Gupta, Vedansh Mittal, K. M. Krishna
Visual servoing has been gaining popularity in various real-world vision-centric robotic applications. Autonomous robotic grasping often deals with unseen and unstructured environments, and in this task, Visual Servoing has been able to generate improved end-effector control by providing visual feedback. However, existing Servoing-aided grasping methods tend to fail at the task of grasping in dynamic environments i.e. - moving objects.In this paper, we introduce DynGraspVS, a novel Image-based Visual Servoing-aided Grasping approach that models the motion of moving objects in its interaction matrix. Leveraging a single-step rollout strategy, our approach achieves a remarkable increase in success rate, while converging faster and achieving a smoother trajectory, while maintaining precise alignments in six degrees of freedom. By integrating the velocity information into the interaction matrix, our method is able to successfully complete the challenging task of robotic grasping in the case of dynamic objects, while outperforming existing deep Model Predictive Control (MPC) based methods in the PyBullet simulation environment. We test it with a range of objects in the YCB dataset with varying range of shapes, sizes, and material properties. We report various evaluation metrics such as photometric error, success rate, time taken, and trajectory length.
{"title":"DynGraspVS: Servoing Aided Grasping for Dynamic Environments","authors":"Gunjan Gupta, Vedansh Mittal, K. M. Krishna","doi":"10.1109/ROBIO58561.2023.10354813","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354813","url":null,"abstract":"Visual servoing has been gaining popularity in various real-world vision-centric robotic applications. Autonomous robotic grasping often deals with unseen and unstructured environments, and in this task, Visual Servoing has been able to generate improved end-effector control by providing visual feedback. However, existing Servoing-aided grasping methods tend to fail at the task of grasping in dynamic environments i.e. - moving objects.In this paper, we introduce DynGraspVS, a novel Image-based Visual Servoing-aided Grasping approach that models the motion of moving objects in its interaction matrix. Leveraging a single-step rollout strategy, our approach achieves a remarkable increase in success rate, while converging faster and achieving a smoother trajectory, while maintaining precise alignments in six degrees of freedom. By integrating the velocity information into the interaction matrix, our method is able to successfully complete the challenging task of robotic grasping in the case of dynamic objects, while outperforming existing deep Model Predictive Control (MPC) based methods in the PyBullet simulation environment. We test it with a range of objects in the YCB dataset with varying range of shapes, sizes, and material properties. We report various evaluation metrics such as photometric error, success rate, time taken, and trajectory length.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"37 2","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-04DOI: 10.1109/ROBIO58561.2023.10354783
Guanhao Xie, Duo Zhao, Qichao Tang, Muhua Zhang, Wenjie Zhao, Yewen Wang
Due to the widespread use of robotic arms, path planning for them has always been a hot research topic. However, traditional path planning algorithms struggle to ensure low disparity in each path, making them unsuitable for operation scenarios with high safety requirements, such as the undercarriage environment of train. A Reinforcement Learning (RL) framework is proposed in this article to address this challenge. The Proximal Policy Optimization (PPO) algorithm has been enhanced, resulting in a variant referred to as Randomized PPO (RPPO), which demonstrates slightly accelerated convergence speed. Additionally, a reward model is proposed to assist the agent in escaping local optima. For modeling application environment, lidar is employed for obtaining obstacle point cloud information, which is then transformed into an octree grid map for maneuvering the robotic arm to avoid obstacles. According to the experimental results, the paths planned by our system are superior to those of RRT* in terms of both average length and standard deviation, and RPPO exhibits better convergence speed and path standard deviation compared to PPO.
{"title":"Path Planning for Robotic Arm Based on Reinforcement Learning under the Train","authors":"Guanhao Xie, Duo Zhao, Qichao Tang, Muhua Zhang, Wenjie Zhao, Yewen Wang","doi":"10.1109/ROBIO58561.2023.10354783","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354783","url":null,"abstract":"Due to the widespread use of robotic arms, path planning for them has always been a hot research topic. However, traditional path planning algorithms struggle to ensure low disparity in each path, making them unsuitable for operation scenarios with high safety requirements, such as the undercarriage environment of train. A Reinforcement Learning (RL) framework is proposed in this article to address this challenge. The Proximal Policy Optimization (PPO) algorithm has been enhanced, resulting in a variant referred to as Randomized PPO (RPPO), which demonstrates slightly accelerated convergence speed. Additionally, a reward model is proposed to assist the agent in escaping local optima. For modeling application environment, lidar is employed for obtaining obstacle point cloud information, which is then transformed into an octree grid map for maneuvering the robotic arm to avoid obstacles. According to the experimental results, the paths planned by our system are superior to those of RRT* in terms of both average length and standard deviation, and RPPO exhibits better convergence speed and path standard deviation compared to PPO.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"34 12","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Currently, the majority of research on humanoid robot basketball shooting focuses on traditional control methods. However, these methods primarily rely on human-robot interaction and fixed shooting patterns to control the robot’s shooting actions, resulting in limited autonomy for the robot. They often require extensive manual design and coding operations, and face challenges in adapting to different shooting scenarios. To address these problems, this paper applies deep reinforcement learning to the basketball shooting task for a humanoid robot. The task environment is based on the basketball shooting competition defined in the FIRA HuroCup. This paper uses the Double DQN algorithm to train the humanoid robot to master end-to-end basketball shooting skills, specifically: The robot takes RGB images captured by its own head camera as input, then decides to take one of three discrete actions, including turning left, turning right, and shooting. In the experimental section, we validate the effectiveness of our approach and conduct an analysis and discussion on the setup of important parameters that influence the experimental results.
{"title":"Deep Reinforcement Learning for a Humanoid Robot Basketball Player","authors":"Shuaiqi Zhang, Guodong Zhao, Peng Lin, Mingshuo Liu, Jianhua Dong, Haoyu Zhang","doi":"10.1109/ROBIO58561.2023.10354565","DOIUrl":"https://doi.org/10.1109/ROBIO58561.2023.10354565","url":null,"abstract":"Currently, the majority of research on humanoid robot basketball shooting focuses on traditional control methods. However, these methods primarily rely on human-robot interaction and fixed shooting patterns to control the robot’s shooting actions, resulting in limited autonomy for the robot. They often require extensive manual design and coding operations, and face challenges in adapting to different shooting scenarios. To address these problems, this paper applies deep reinforcement learning to the basketball shooting task for a humanoid robot. The task environment is based on the basketball shooting competition defined in the FIRA HuroCup. This paper uses the Double DQN algorithm to train the humanoid robot to master end-to-end basketball shooting skills, specifically: The robot takes RGB images captured by its own head camera as input, then decides to take one of three discrete actions, including turning left, turning right, and shooting. In the experimental section, we validate the effectiveness of our approach and conduct an analysis and discussion on the setup of important parameters that influence the experimental results.","PeriodicalId":505134,"journal":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"45 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139187376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：