首页|Studies from Harbin Institute of Technology Provide New Data on Robotics (Ria-cs m2: a Real-time Impact-aware Correlative Scan Matching Algorithm Using Heterogen eous Multicore Soc for Lowcost Wheeled Robots)
Studies from Harbin Institute of Technology Provide New Data on Robotics (Ria-cs m2: a Real-time Impact-aware Correlative Scan Matching Algorithm Using Heterogen eous Multicore Soc for Lowcost Wheeled Robots)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
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."
HarbinPeople's Republic of ChinaAsiaAlgorithmsEmerging TechnologiesMachine LearningNano-robotRobotRoboti csHarbin Institute of Technology
NETL
NSTL
