首页|Reports on Robotics Findings from INESC Provide New Insights (Fusion of Time-of- flight Based Sensors With Monocular Cameras for a Robotic Person Follower)

Reports on Robotics Findings from INESC Provide New Insights (Fusion of Time-of- flight Based Sensors With Monocular Cameras for a Robotic Person Follower)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting originating in Porto, Portugal, by Ne wsRx journalists, research stated, "Human-robot collaboration (HRC) is becoming increasingly important in advanced production systems, such as those used in ind ustries and agriculture. This type of collaboration can contribute to productivi ty increase by reducing physical strain on humans, which can lead to reduced inj uries and improved morale." Financial support for this research came from H2020 European Institute of Innova tion and Technology. The news reporters obtained a quote from the research from INESC, "One crucial a spect of HRC is the ability of the robot to follow a specific human operator saf ely. To address this challenge, a novel methodology is proposed that employs mon ocular vision and ultra-wideband (UWB) transceivers to determine the relative po sition of a human target with respect to the robot. UWB transceivers are capable of tracking humans with UWB transceivers but exhibit a significant angular erro r. To reduce this error, monocular cameras with Deep Learning object detection a re used to detect humans. The reduction in angular error is achieved through sen sor fusion, combining the outputs of both sensors using a histogram-based filter . This filter projects and intersects the measurements from both sources onto a 2D grid. By combining UWB and monocular vision, a remarkable 66.67% reduction in angular error compared to UWB localization alone is achieved. This approach demonstrates an average processing time of 0.0183s and an average local ization error of 0.14 meters when tracking a person walking at an average speed of 0.21 m/s."

PortoPortugalEuropeEmerging Techno logiesMachine LearningRobotRoboticsRobotsINESC

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Mar.6)