Bio-inspired vision based robot control using featureless estimations of time-to-contact

Zhang Haijie; Zhao Jianguo

首页> 外文期刊>Bioinspiration & biomimetics >Bio-inspired vision based robot control using featureless estimations of time-to-contact

【24h】

Bio-inspired vision based robot control using featureless estimations of time-to-contact

机译：生物启发的基于视觉的机器人控制，使用无言的估算时间 - 联系

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Marvelous vision based dynamic behaviors of insects and birds such as perching, landing, and obstacle avoidance have inspired scientists to propose the idea of time-to-contact, which is defined as the time for a moving observer to contact an object or surface if the current velocity is maintained. Since with only a vision sensor, time-to-contact can be directly estimated from consecutive images, it is widely used for a variety of robots to fulfill various tasks such as obstacle avoidance, docking, chasing, perching and landing. However, most of existing methods to estimate the time-to-contact need to extract and track features during the control process, which is time-consuming and cannot be applied to robots with limited computation power. In this paper, we adopt a featureless estimation method, extend this method to more general settings with angular velocities, and improve the estimation results using Kalman filtering. Further, we design an error based controller with gain scheduling strategy to control the motion of mobile robots. Experiments for both estimation and control are conducted using a customized mobile robot platform with low-cost embedded systems. Onboard experimental results demonstrate the effectiveness of the proposed approach, with the robot being controlled to successfully dock in front of a vertical wall. The estimation and control methods presented in this paper can be applied to computation-constrained miniature robots for agile locomotion such as landing, docking, or navigation.

机译：基于昆虫和鸟类的昆虫视觉行为，如栖息，着陆和障碍物避免的昆虫和鸟类的动态行为使科学家们提出了时间 - 接触的思想，这被定义为移动观察者与物体或表面接触的时间保持当前的速度。由于只有视觉传感器，可以从连续图像直接估计时间 - 接触，因此广泛用于各种机器人来满足各种任务，如障碍避免，对接，追逐，栖息和着陆。然而，大多数现有方法来估计在控制过程期间提取和跟踪特征的现有方法，这是耗时的，并且不能应用于具有有限计算能力的机器人。在本文中，我们采用一种无特色估计方法，将这种方法扩展到具有角速度的更常规设置，并使用卡尔曼滤波改进估计结果。此外，我们设计了基于错误的控制器，具有增益调度策略来控制移动机器人的运动。使用具有低成本嵌入式系统的定制移动机器人平台进行估计和控制的实验。车载实验结果表明了所提出的方法的有效性，机器人被控制在垂直墙壁前成功码头。本文提出的估计和控制方法可以应用于计算受限的微型机器人，用于达到敏捷运动，例如着陆，对接或导航。

著录项

来源
《Bioinspiration & biomimetics》 |2017年第2期|共11页
作者
Zhang Haijie; Zhao Jianguo;
展开▼
作者单位

Colorado State Univ Dept Mech Engn Ft Collins CO 80523 USA;

Colorado State Univ Dept Mech Engn Ft Collins CO 80523 USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类生物工程学（生物技术）;
关键词
biologically inspired robotics; vision based control; time-to-contact; biomimetics;

机译：生物启发机器人;基于视觉的控制;时间 - 接触;生物体;

相似文献

外文文献
中文文献
专利

1. Bio-inspired vision based robot control using featureless estimations of time-to-contact [J] . Zhang Haijie, Zhao Jianguo Bioinspiration & biomimetics . 2017,第2期

机译：生物启发的基于视觉的机器人控制，使用无言的估算时间 - 联系
2. Ocular pursuit and the estimation of time-to-contact with accelerating objects in prediction motion are controlled independently based on first-order estimates [J] . Nicolas Benguigui, Simon J. Bennett Experimental Brain Research . 2010,第2期

机译：基于一阶估计，独立控制眼球追踪和预测运动中与加速物体的接触时间的估计
3. Toward Coordination Control of Multiple Fish-Like Robots: Real-Time Vision-Based Pose Estimation and Tracking via Deep Neural Networks [J] . Tianhao Zhang, Jiuhong Xiao, Liang Li, 自动化学报（英文版） . 2021,第012期

机译：Toward Coordination Control of Multiple Fish-Like Robots: Real-Time Vision-Based Pose Estimation and Tracking via Deep Neural Networks
4. Biologically inspired vision based control using featureless time-to-contact estimations [C] . Haijie Zhang, Jianguo Zhao IEEE International Conference on Advanced Intelligent Mechatronics . 2016

机译：基于生物启发的基于视觉的控制，使用无特征的接触时间估算
5. Towards Building Autonomy and Intelligence for Surgical Robotic Systems Using Trajectory Optimization, Stochastic Estimation, Vision-Based Control, and Machine Learning Algorithms [D] . Aghajani Pedram, Sahba. 2020

机译：利用轨迹优化，随机估计，基于视觉控制和机器学习算法建立外科机器人系统的自主权和智能
6. ED-BioRob: A Neuromorphic Robotic Arm With FPGA-Based Infrastructure for Bio-Inspired Spiking Motor Controllers [O] . Alejandro Linares-Barranco, Fernando Perez-Peña, Angel Jimenez-Fernandez, 2020

机译：Ed-Biorob：具有基于FPGA的基础设施的神经形状机器人用于生物启发尖刺电机控制器
7. Development of a Bio-inspired Vision System for Mobile Micro-robots:In this paper, we present a new bio-inspired vision system for mobile micro-robots. The processing method takes inspiration from vision of locusts in detecting the fast approaching objects. Research suggested that locusts use wide-field visual neuron called the lobula giant movement detector to respond to imminent collisions. We employed the locusts' vision mechanism to motion control of a mobile robot. The selected image processing method is implemented on a developed extension module using a low-cost and fast ARM processor. The vision module is placed on top of a micro-robot to control its trajectory and to avoid obstacles. The observed results from several performed experiments demonstrated that the developed extension module and the inspired vision system are feasible to employ as a vision module for obstacle avoidance and motion control. [O] . Hu, Cheng, Arvin, Farshad, Yue, Shigang 2014

机译：开发用于移动微型机器人的生物启发视觉系统：在本文中，我们提出了一种用于移动微型机器人的新型生物启发视觉系统。该处理方法从检测快速接近物体的蝗虫视觉中获取灵感。研究表明，蝗虫使用称为小叶巨型运动探测器的宽视野神经元来应对即将发生的碰撞。我们采用蝗虫的视觉机制来控制移动机器人。所选择的图像处理方法使用低成本且快速的aRm处理器在开发的扩展模块上实现。视觉模块放置在微型机器人的顶部以控制其轨迹并避开障碍物。几次进行的实验观察到的结果表明，开发的扩展模块和灵感视觉系统可用作避障和运动控制的视觉模块。

Bio-inspired vision based robot control using featureless estimations of time-to-contact

摘要

著录项

相似文献

相关主题

期刊订阅