Multimodal trajectory optimization for motion planning

Abstract

Existing motion planning methods often have two drawbacks: (1) goal configurations need to be specified by a user, and (2) only a single solution is generated under a given condition. In practice, multiple possible goal configurations exist to achieve a task. Although the choice of the goal configuration significantly affects the quality of the resulting trajectory, it is not trivial for a user to specify the optimal goal configuration. In addition, the objective function used in the trajectory optimization is often non-convex, and it can have multiple solutions that achieve comparable costs. In this study, we propose a framework that determines multiple trajectories that correspond to the different modes of the cost function. We reduce the problem of identifying the modes of the cost function to that of estimating the density induced by a distribution based on the cost function. The proposed framework enables users to select a preferable solution from multiple candidate trajectories, thereby making it easier to tune the cost function and obtain a satisfactory solution. We evaluated our proposed method with motion planning tasks in 2D and 3D space. Our experiments show that the proposed algorithm is capable of determining multiple solutions for those tasks.

Benchmarking and optimization of robot motion planning with motion planning pipeline

“…This method is different from CHOMP in that it is optimized by a specific optimization algorithm and does not require gradient information. In recent years, CHOMP and STOMP have also received great attention and further research [29][30][31]. In this article, we use the planning request adapter in Moveit to modify the trajectory created by the sampling algorithm in OMPL.…”

Robot Motion Planning Benchmarking and Optimization using Motion Planning Pipeline

“…This method is different from CHOMP in that it is optimized by a speci c optimization algorithm and does not require gradient information. In recent years, CHOMP and STOMP have also received great attention and further research [33][34][35]. In this article, we use the planning request adapter in Moveit to modify the trajectory created by the sampling algorithm in OMPL.…”

Self-protective motion planning for mobile manipulators in a dynamic door-closing workspace

“…If a node with belief b has a child node with belief b', then b' = p(b,a,z). Conceptually, we may think of POMDP planning as a tree search in the belief space, the space of all possible beliefs that the mobile manipulator may encounter (Osa, 2020). To find an optimal plan for a POMDP, we traverse the belief tree from the bottom up and compute an optimal action recursively at each node using Bellman's equation (Thrun, 2002):…”