Topic
Motion planning
About: Motion planning is a research topic. Over the lifetime, 32846 publications have been published within this topic receiving 553548 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: It is shown that planning in belief space can be performed efficiently for linear Gaussian systems by using a factored form of the covariance matrix, allowing several prediction and measurement steps to be combined into a single linear transfer function, leading to very efficient posterior belief prediction during planning.
Abstract: When a mobile agent does not know its position perfectly, incorporating the predicted uncertainty of future position estimates into the planning process can lead to substantially better motion performance However, planning in the space of probabilistic position estimates, or belief space, can incur a substantial computational cost In this paper, we show that planning in belief space can be performed efficiently for linear Gaussian systems by using a factored form of the covariance matrix This factored form allows several prediction and measurement steps to be combined into a single linear transfer function, leading to very efficient posterior belief prediction during planning We give a belief-space variant of the probabilistic roadmap algorithm called the belief roadmap (BRM) and show that the BRM can compute plans substantially faster than conventional belief space planning We conclude with performance results for an agent using ultra-wide bandwidth radio beacons to localize and show that we can efficiently generate plans that avoid failures due to loss of accurate position estimation
331 citations
TL;DR: Two demonstrator platforms for a robotic home assistant—called Care-O-bot—were designed and implemented at Fraunhofer IPA, Stuttgart and a new method for sensor based manipulation using a tilting laser scanner and camera integrated in the head of the robot has been implemented.
Abstract: Technical aids allow elderly and handicapped people to live independently and supported in their private homes for a longer time. As a contribution to such technological solutions, two demonstrator platforms for a robotic home assistant—called Care-O-bot—were designed and implemented at Fraunhofer IPA, Stuttgart. Whereas Care-O-bot I is only a mobile platform with a touch screen, Care-O-bot II is additionally equipped with adjustable walking supporters and a manipulator arm. It has the capability to navigate autonomously in indoor environments, be used as an intelligent walking support, and execute manipulation tasks. The control software of Care-O-bot II runs on two industrial PCs and a hand-held control panel. The walking aid module is based on sensors in the walking aid handles and on a dynamic model of conventional walking aids. In “direct mode”, the user can move along freely with the robot whereas obstacles are detected and avoided. In “planned mode”, he can specify a target and be lead there by the robotic assistant. Autonomous planning and execution of complex manipulation tasks is based on a symbolic planner and environmental information provided in a database. The user input (graphical and speech input) is transferred to the task planner and adequate actions to solve the task (sequence of motion and manipulation commands) are created. A new method for sensor based manipulation using a tilting laser scanner and camera integrated in the head of the robot has been implemented. Additional sensors in the robot hand increase the grasping capabilities. The walking aid has been tested with elderly users from an assisted living facility and a nursery home. Furthermore, the execution of fetch and carry tasks has been implemented and tested in a sample home environment.
331 citations
TL;DR: Several new operations/improvements such as the particle update method based on random sampling and uniform mutation, the infeasible archive, the constrained domination relationship based on collision times with obstacles, are incorporated into the proposed algorithm to improve its effectiveness.
328 citations
08 Apr 2015
TL;DR: This paper proposes an energy-aware path planning algorithm that minimizes energy consumption while satisfying a set of other requirements, such as coverage and resolution, based on an energy model derived from real measurements.
Abstract: Coverage path planning is the operation of finding a path that covers all the points of a specific area. Thanks to the recent advances of hardware technology, Unmanned Aerial Vehicles (UAVs) are starting to be used for photogrammetric sensing of large areas in several application domains, such as agriculture, rescuing, and surveillance. However, most of the research focused on finding the optimal path taking only geometrical constraints into account, without considering the peculiar features of the robot, like available energy, weight, maximum speed, sensor resolution, etc. This paper proposes an energy-aware path planning algorithm that minimizes energy consumption while satisfying a set of other requirements, such as coverage and resolution. The algorithm is based on an energy model derived from real measurements. Finally, the proposed approach is validated through a set of experiments.
328 citations
01 Jan 1998
328 citations