Strategies for Speeding Up Manipulator Path Planning to Find High Quality Paths in Cluttered Environments

Abstract

In many manufacturing applications, robotic manipulators need to operate in cluttered environments. quickly finding high quality paths is very important in such applications. This paper presents a point-to-point path planning framework for manipulators operating in cluttered environments. It facilitates finding a balance between path quality and planning time. The framework dynamically switches between various strategies to produce high-quality paths quickly. In this work, (1) we extend a previously developed sampling-based modular tree-search, (2) we add new strategies and scheduling logic that decreases the failure rate as well as the planning time compared to our prior work, (3) we also present theoretical reasoning behind strategy switching and how it can help decrease planning times and increase path quality. Specifically, we present a strategy that can sample effectively in challenging regions of the search-space by using local approximations of the configuration space. We also present an inter-tree connection strategy that adapts to collision information gathered over time. We introduce a scheduling rule that regulates the exploitation of focusing hints derived from the workspace obstacles. Together, these new extensions the reduce average failure rate by a factor of 4 and improve the average planning time by 22% over previous work.

Area-Coverage Planning for Spray-based Surface Disinfection with a Mobile Manipulator

“…The area coverage paths generated need to be followed by the robot, which requires the use of constraint motion planning algorithms. Researchers have explored sampling-based approaches to generate constrained point-to-point trajectories for high-DOF robotic systems like manipulators and mobile manipulators [52] , [53] , [54] , [55] , [56] , [57] , [58] as well as mobile robots [59] , [60] . Dalibard et al.…”

Planificación de movimiento mediante algoritmo de campos potenciales con optimizacion de parametros aplicado a un manipulador antropomorfico de 6 GLD

“…MLPRegressor(hidden_layer_sizes= (10), verbose = True, activation = 'relu', solver = 'adam', alpha = 0.0001, batch_size = 'auto', learning_rate = 'constant', learning_rate_init = 0.05, max_iter = 10000, tol = 0.0001, momentum = 0.9, early_stopping = False, epsilon = 1e-08) El proceso de la generación de trayectorias con la aplicación de la red neuronal se visualiza en el siguiente diagrama (figura 6). Donde, para realizar una trayectoria, inicialmente se introducen los vectores de posicionamiento y la posición del obstáculo, luego la red neuronal calcula los parámetros óptimos para dicha trayectoria que son ingresados al modelo de geometría inversa para ejecutar el movimiento en simulación.…”

“…Sin embargo, también han sido implementados en simulación de manipuladores altamente redundantes [8], [9]. Asimismo, Rajendran [10] desarrolla un método de planificación de movimiento aplicado a manipuladores robóticos que se encuentran en espacios desorganizados y con muchos obstáculos. Su técnica se basa en aproximaciones locales de su espacio de configuraciones y también se basa en arboles de búsquedas.…”

Generation of synchronized configuration space trajectories with workspace path constraints for an ensemble of robots

“…We can consider sampling-based approaches for generating the complete trajectory as a whole. Sampling-based approaches have proven to be very efficient in generating motion plans, to be specific point-to-point trajectories, for high-DOF robotic systems (Gammell et al, 2015; Kabir et al, 2018b; Rajendran et al, 2021, 2019a,b,c; Rickert et al, 2014; Thakar et al, 2020b). These methods generate the trajectory in configuration space to connect a specified start and goal configuration.…”