2021 IEEE/SICE International Symposium on System Integration (SII)最新文献_第10页

Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player 加速模拟到真实的深度强化学习:从人类玩家那里学习避免碰撞

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382693

Hanlin Niu, Ze Ji, F. Arvin, B. Lennox, Hujun Yin, J. Carrasco

{"title":"Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player","authors":"Hanlin Niu, Ze Ji, F. Arvin, B. Lennox, Hujun Yin, J. Carrasco","doi":"10.1109/IEEECONF49454.2021.9382693","DOIUrl":"https://doi.org/10.1109/IEEECONF49454.2021.9382693","url":null,"abstract":"This paper presents a sensor-level mapless collision avoidance algorithm for use in mobile robots that map raw sensor data to linear and angular velocities and navigate in an unknown environment without a map. An efficient training strategy is proposed to allow a robot to learn from both human experience data and self-exploratory data. A game format simulation framework is designed to allow the human player to tele-operate the mobile robot to a goal and human action is also scored using the reward function. Both human player data and self-playing data are sampled using prioritized experience replay algorithm. The proposed algorithm and training strategy have been evaluated in two different experimental configurations: Environment 1, a simulated cluttered environment, and Environment 2, a simulated corridor environment, to investigate the performance. It was demonstrated that the proposed method achieved the same level of reward using only 16% of the training steps required by the standard Deep Deterministic Policy Gradient (DDPG) method in Environment 1 and 20% of that in Environment 2. In the evaluation of 20 random missions, the proposed method achieved no collision in less than 2 h and 2.5 h of training time in the two Gazebo environments respectively. The method also generated smoother trajectories than DDPG. The proposed method has also been implemented on a real robot in the real-world environment for performance evaluation. We can confirm that the trained model with the simulation software can be directly applied into the real-world scenario without further fine-tuning, further demonstrating its higher robustness than DDPG. The video and code are available: https://youtu.be/BmwxevgsdGc https://github.com/hanlinniu/turtlebot3_ddpg_collision_avoidance","PeriodicalId":395378,"journal":{"name":"2021 IEEE/SICE International Symposium on System Integration (SII)","volume":"436 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116553579","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}

引用次数: 16

Generating Curved Path Walking Gaits for Biped Robots with Deficient Degrees of Freedom 缺乏自由度双足机器人曲线路径步行步态的生成

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382698

K. Venkatesan, Prajwal Rajendra Mahendrakar

引用次数: 1

A long-time automated honeybees count system using high-speed vision 一种使用高速视觉的长期自动化蜜蜂计数系统

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382778

H. Yoshida, Kohei Shimasaki, T. Senoo, I. Ishii, Kazuhiko Yamamoto

引用次数: 0

The Effect of Passive Lower Limb Assist Device on Muscle Synergy in Standing-Up Motion 被动下肢辅助装置对站立运动肌肉协同作用的影响

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382626

S. Torigai, Takayuki Tanaka

引用次数: 0

Consideration about Structure of Gait Motion Assist Device for Trunk Using McKibben Type Pneumatic Artificial Muscle 基于McKibben型气动人工肌肉的躯干步态运动辅助装置结构的思考

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382615

Hayato Yase, D. Sasaki, Jun Kadowaki, Taiga Kimura

引用次数: 0

Improved Scan Matching Performance in Snowy Environments Using Semantic Segmentation 利用语义分割改进雪域环境下扫描匹配性能

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382713

M. Obuchi, T. Emaru, Ankit A. Ravankar

引用次数: 1

Basic Evaluation of Carbonate Stimulus Amplification and Taste Change Using AC Electric Stimulation 交流电刺激对碳酸盐刺激放大和味觉变化的基本评价

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382782

Jumpei Kanayama, Ibuki Nomura, Noriki Mochizuki, Takafumi Koike, Sousuke Nakamura

引用次数: 1

An Energy Based Control for Vibration Suppression in a Rigid Parallel Series Elastic Actuator 基于能量的刚性并联串联弹性作动器减振控制

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382723

U. Mavinkurve, Seyed Amir Tafrishi, Ayato Kanada, Motoji Yamamoto

引用次数: 1

Behavioral Cloning from Observation with Bi-directional Dynamics Model 基于双向动力学模型的观察行为克隆

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382751

Tobias Betz, Hidehito Fujiishi, Taisuke Kobayashi

{"title":"Behavioral Cloning from Observation with Bi-directional Dynamics Model","authors":"Tobias Betz, Hidehito Fujiishi, Taisuke Kobayashi","doi":"10.1109/IEEECONF49454.2021.9382751","DOIUrl":"https://doi.org/10.1109/IEEECONF49454.2021.9382751","url":null,"abstract":"Robotics is rapidly expanding its workplace from industrial factories to more complicated fields to work on behalf of human. The difficulty of programing the operations human does in advance, however, prevents this expansion. Behavioral cloning is one of the promising approaches to acquire the operations effectively from the expert’s demonstrations, which consist of the states and the performed actions of the expert. However, it is intractable and/or highly expensive for robots to measure the expert’s actions. Behavioral cloning from observation fills this gap and makes it possible to imitate with state-only demonstrations by inferring actions that the expert performed from an inverse dynamics model. Our goal is to improve the accuracy of this algorithm. This is done by evaluating the inferred action using an additional forward dynamics model. Specifically, we focus on the consistency in both dynamics models, which have to be bi-directional. This bi-directionality, can classify whether the inferred action is realistic or not, and can prevent wrong updates. We show the successful improvement with our new method using various simulation tasks which are typically used in benchmarks.","PeriodicalId":395378,"journal":{"name":"2021 IEEE/SICE International Symposium on System Integration (SII)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131625341","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}

引用次数: 1

Development of high-speed gripper with closing and releasing capability 具有闭合和释放功能的高速夹持器的研制

2021 IEEE/SICE International Symposium on System Integration (SII) Pub Date : 2021-01-11 DOI: 10.1109/IEEECONF49454.2021.9382704

Ryosuke Iwazawa, K. Ohara, M. Kaneko

引用次数: 1