Findings from Vrije Universiteit Brussel (VUB) Yields New Data on Robotics (Real -time Constraint-based Planning and Control of Robotic Manipulators for Safe Hum an-robot Collaboration)
Findings from Vrije Universiteit Brussel (VUB) Yields New Data on Robotics (Real -time Constraint-based Planning and Control of Robotic Manipulators for Safe Hum an-robot Collaboration)
由一名新闻记者兼机器人与机器学习的新闻编辑每日新闻-一项关于机器人的新研究现在开始了。根据NewsRx编辑在比利时布鲁塞尔的新闻报道，Research表示：“工业机器人学的最新趋势是机器人操作器与人类操作员并肩工作。这种COE现状的一个挑战在于，机器人需要在动态变化的环境中可靠地解决复杂的路径规划问题。”我们的新闻记者从Vrije Universiteit Brussel(VUB)的研究中获得了一句话，“为了确保人类操作员的安全，同时实现有效的任务实现，”本文介绍了一种快速探索的Rand OM Tree(RRT)路径规划器与基于轨迹的显式参考调节器(ERG)相结合的高效规划与控制结构,该方案在执行器饱和、关节范围受限、速度限制、静态障碍物环境混乱等情况下,能够将机器人手臂控制到期望的末端执行器姿态。在Franka Emika Panda机器人手臂上的实验验证了该方法的有效性,在复杂的静态环境下,该方法优于独立的RT和ERG算法,克服了:1)RT不能处理动态约束导致约束违反和2)ERG不理想的特性。陷入局部极小值的陷阱。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Robotics is now availab le. According to news reporting out of Brussels, Belgium, by NewsRx editors, res earch stated, “A recent trend in industrial robotics is to have robotic manipula tors working side-by-side with human operators. A challenging aspect of this coe xistence is that the robot is required to reliably solve complex path-planning p roblems in a dynamically changing environment.” Our news journalists obtained a quote from the research from Vrije Universiteit Brussel (VUB), “To ensure the safety of the human operator while simultaneously achieving efficient task realization, this paper introduces a computationally ef ficient planning and control architecture that combines a Rapidly-exploring Rand om Tree (RRT) path planner with a trajectory-based Explicit Reference Governor ( ERG) by means of a reference selector. The resulting scheme can steer the robot arm to the desired end-effector pose in the presence of actuator saturation, lim ited joint ranges, speed limits, a cluttered static obstacle environment, and mo ving human collaborators. The effectiveness of the proposed framework is experim entally validated on the Franka Emika Panda robot arm and fed with feedback info rmation from state-of-the-art depth perception systems. Our method outperforms b oth the standalone RRT and ERG algorithms in cluttered static environments where it overcomes: i) the RRT’s inability to handle dynamic constraints which result in constraint violations and ii) the ERG’s undesirable property of getting trap ped in local minima.”
NETL
NSTL