Autonomous navigation often requires the simultaneous optimization of multiple objectives. The most common approach scalarizes these into a single cost function using a weighted sum, but this method is unable to find all possible trade-offs and can therefore miss critical solutions. An alternative, the weighted maximum of objectives, can find all Pareto-optimal solutions, including those in non-convex regions of the trade-off space that weighted sum methods cannot find. However, the increased computational complexity of finding weighted maximum solutions in the discrete domain has limited its practical use. To address this challenge, we propose a novel search algorithm based on the Large Neighbourhood Search framework that efficiently solves the weighted maximum planning problem. Through extensive simulations, we demonstrate that our algorithm achieves comparable solution quality to existing weighted maximum planners with a runtime improvement of 1-2 orders of magnitude, making it a viable option for autonomous navigation.
Multi-Modal Active Perception for Information Gathering in Science Missions
Australian Centre for Field Robotics, The University of Sydney(悉尼大学澳大利亚野外机器人中心);Center for Autonomous Systems, University of Technology Sydney(悉尼科技大学自主系统中心);Intelligent Robotics Group, NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心智能机器人组)
Manipulability Maximization Using Continuous-Time Gaussian Processes
University of Toronto(多伦多大学);University of Zagreb, Faculty of Electrical Engineering and Computing(萨格勒布大学电气工程与计算学院)
运动规划中的一个重大挑战是避免处于或靠近\emph{singular configurations}(\textit{singularities}),即,导致在任务空间中沿某些方向移动的能力丧失的关节配置。机器人系统的运动能力甚至在非常接近(即,一个奇点(Singularity)。在这项工作中,我们研究奇异避免在运动规划的背景下,找到轨迹,最大限度地减少接近奇异区域,受到约束。我们定义了一个基于可操作性的可能性与奇异性避免在连续的轨迹表示,然后我们最大限度地使用\textit{maximum a posteriori}(MAP)估计。将MAP问题视为因子图上的推理,我们使用内插状态的梯度信息来最大化轨迹的整体可操作性。实验数据的定性和定量分析表明,可操作性的增加,导致在平滑的轨迹与明显更灵巧的手臂配置。