Harmonious Sampling for Mobile Manipulation Planning

Abstract

Mobile manipulation planning commonly adopts a decoupled approach that performs planning separately on the base and the manipulator. While this approach is fast, it can generate sub-optimal paths. Another direction is a coupled approach jointly adjusting the base and manipulator in a high-dimensional configuration space. This coupled approach addresses sub-optimality and incompleteness of the decoupled approach, but has not been widely used due to its excessive computational overhead. Given this trade-off space, we present a simple, yet effective mobile manipulation sampling method, harmonious sampling, to perform the coupled approach mainly in difficult regions, where we need to simultaneously maneuver the base and the manipulator. Our method identifies such difficult regions through a low-dimensional base space by utilizing a reachability map given the target end-effector pose and narrow passage detected by generalized Voronoi diagram. For the rest of simple regions, we perform sampling mainly on the base configurations with a predefined joint configuration, accelerating the planning process. We compare our method with the decoupled and coupled approaches in six different problems with varying difficulty. Our method shows meaningful improvements experimentally in terms of time to find an initial solution (up to 5.6 times faster) and final solution cost (up to 17% lower) over the decoupled approach, especially in difficult scenes with narrow space. We also demonstrate these benefits with a real, mobile Hubo robot.

Heterogeneous Dimensionality Reduction for Efficient Motion Planning in High-Dimensional Spaces

“…Although we present a unified optimization-based trajectory planning approach that operates in multiple subspaces, other generic trajectory planning methods could also be applied to solve multi-subspace planning problems, such as the sampling-and search-based methods [30].…”

“…The start position is relatively far away from the goal, as shown in Fig. 7 and the planning task involves planning a collision-free trajectory for the base and arm from the start configuration to the goal in a coupled way [1], [30].…”

“…For a given task, the number of samples could also be determined by the running time limits of the algorithm. Other workspace analysis method can also be applied to the bias the sampling, such as the Generalized Voronoi Graph-based (GVG) narrow passages search [30] and learning-based non-uniform sampling strategies proposed in [12]. In those works, more points are sampled at the narrow passages areas or other important areas.…”

Fast Perception, Planning, and Execution for a Robotic Butler: Wheeled Humanoid M-Hubo

“…In addition, learning strategies can be utilized in the future to reduce failures, uncertainties, and unsafe states to increase success rate. Lastly, overall execution time can be further reduced even in dynamic environments by incorporating faster sampling motion planners described in this work [22].…”

Reactive Self-Collision Avoidance for a Differentially Driven Mobile Manipulator

“…Kang et al. [ 9 ] proposed a sampling-based method that efficiently explores whole-body configuration space by sampling more around a region close to obstacles. However, these methods are difficult to implement in unstructured and dynamic environments because trajectories may have to be regenerated in real time.…”