摘要
由一名新闻记者-机器人和机器学习每日新闻的工作人员新闻编辑-一项关于机器人的新研究现在可以获得。根据NewsRx编辑S在哈尔滨的新闻报道，研究表明：“作为一种经典的扫描地图匹配方法，如果低成本轮式机器人（如机器人清洁器）受到影响，相关的S CAN匹配(CSM)算法可能不适用。第一个公开的问题是严重依赖可调整的初始姿态。”本研究经费来源于国家重点研究开发项目。我们的新闻记者从哈尔滨工业大学的研究中获得了一句话:“安装在轮子上的旋转编码器由于撞击引起的侧滑是无法观察到的,导致了巨大的定位误差。第二个开放的问题是使用CSM算法进行全球定位的有效处理。”摘要:针对大型多分辨率惯性导航系统的硬件设计存在能量效率低的问题,提出了一种基于轻量级de ep神经网络的碰撞检测方法,该方法仅使用低成本的本体感知传感器,就可以在未知环境下进行可靠的碰撞检测。针对传统轮辅助惯性导航系统(INSs)误差快速增长的问题,提出了一种基于轻量级de ep神经网络的碰撞检测方法。CSM算法的延迟失序测量被集成到扩展的Kalman Filter(EKF)中。轻量级碰撞检测网络和惯性导航系统通常适用于大多数具有严格能量、计算和存储成本限制的嵌入式机器人系统。一旦检测到碰撞，基于公共数据集的大规模多分辨率CSM算法实验表明,该算法具有较高的实时性和能量效率,局部尺度高分辨率CSM算法的帧速率可达96.42帧/s。在轮式机器人平台上的现场实验证明了该算法的有效性。该算法在准确率和误警率方面都有很大的提高，准确率和召回率分别达到100%和97.8%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-A new study on Robotics is now available. Accordi ng to news reporting out of Harbin, People's Republic of China, by NewsRx editor s, research stated, "As a classic scan-to-map matching method, the correlative s can matching (CSM) algorithm may not be applicable if low-cost wheeled robots (l ike robot cleaners) are impacted. The first open issue is heavy dependence on tr ustworthy initial poses." Financial support for this research came from National Key Research and Developm ent Program of China. Our news journalists obtained a quote from the research from the Harbin Institut e of Technology, "Side slips caused by impacts are unobservable for rotary encod ers mounted on wheels, leading to huge localization errors. The second open issu e is the efficient processing of global localization using the CSM algorithm, wh ich is essential for impacted robots. The state-of-the-art hardware designs for large-scale multiresolution CSM have low energy efficiency. These two open issue s are properly addressed in this work, namely, RIA-CSM2. Based on lightweight de ep neural networks, we perform reliable impact detection in unforeseen environme nts using only low-cost proprioceptive sensors. To bind the rapid error growth o f conventional wheel-aided inertial navigation systems (INSs), delayed out-of-se quence measurements from CSM algorithms are integrated into an extended Kalman f ilter (EKF). The lightweight impact detection networks and INS are generally app licable for most embedded robotic systems with stringent energy, computing, and memory cost limitations. Once impacts are detected, large-scale multiresolution CSM algorithms will be performed on an energy-efficient hardware accelerator. Ex tensive experiments based on public datasets show that our work achieves high re al-time performance and energy efficiency. The frame rate of local-scale high-re solution CSM can reach up to 96.42 frames/s. Field experiments on wheeled robot platforms demonstrate the effectiveness of our impact detection network, which o utperforms our preliminary work in precision and false-alarm rate by a significa nt margin, with precision and recall rates reaching 100% and 97.8% , respectively."
NETL
NSTL