Abstract-Rapidly-exploring Random Trees (RRTs) are widely used to solve large planning problems where the scope prohibits the feasibility of deterministic solvers, but the efficiency of these algorithms can be severely compromised in the presence of certain kinodynamics constraints. Obstacle fields with tunnels, or tubes are notoriously difficult, as are systems with differential constraints, because the tree grows inefficiently at the boundaries. Here we present a new sampling strategy for the RRT algorithm, based on an estimated feasibility set, which affords a dramatic improvement in performance in these severely constrained systems. We demonstrate the algorithm with a detailed look at the expansion of an RRT in a swingup task, and on path planning for a nonholonomic car. I. INTRODUCTIONThe problem of robotic motion planning, whether for a wheeled robot, an aerial vehicle, or a quadruped, has motivated the development of powerful tools for planning in high dimensional spaces. Of these techniques, randomized sample-based planning strategies have proven particularly effective in quickly solving for a series of actions that drive the system to a desired state. Perhaps the most widely used single-query sample-based planners are those based upon Rapidly-exploring Randomized Trees (RRTs). RRTs have been used to solve a broad range of planning problems that include motion for manipulators and kinematic chains [1], [2].It is well-known that these algorithms can quickly become inefficient when planning on systems with complicated kinodynamic constraints [3], and there has been considerable work in attempting to modify the basic RRT algorithm for these situations [3], [4]. The essential symptom of this inefficiency is that nodes at the boundaries of these constraints tend to be sampled and expanded repeatedly, with little progress towards the ultimate goal.In this paper, we present a modified adaptive sampling strategy for the RRT algorithm which takes into account local reachability, as defined by differential constraints, while building the tree. The algorithm is based on the observation that sampling points at random and checking collisions is relatively cheap, but adding extra nodes to the tree (through the Extend algorithm) is relatively more expensive -both in its instantaneous cost and in the added cost of having a larger tree. Therefore, we attempt to build sparse trees through kinodynamic obstacles, with a simple heuristic that quickly throws away random samples that otherwise would not have the effect of extending the tree into previously unexplored regions of state space. This effectively changes the sampling distribution, so that points are selected uniformly from a
Abstract-The reduction of the kinematics and/or dynamics of a high-DOF robotic manipulator to a low-dimension "task space" has proven to be an invaluable tool for designing feedback controllers. When obstacles or other kinodynamic constraints complicate the feedback design process, motion planning techniques can often still find feasible paths, but these techniques are typically implemented in the high-dimensional configuration (or state) space. Here we argue that providing a Voronoi bias in the task space can dramatically improve the performance of randomized motion planners, while still avoiding non-trivial constraints in the configuration (or state) space. We demonstrate the potential of task-space search by planning collision-free trajectories for a 1500 link arm through obstacles to reach a desired end-effector position.
Abstract. We embodied networks of cultured biological neurons in simulation and in robotics. This is a new research paradigm to study learning, memory, and information processing in real time: the Neurally-Controlled Animat. Neural activity was subject to detailed electrical and optical observation using multi-electrode arrays and microscopy in order to access the neural correlates of animat behavior. Neurobiology has given inspiration to AI since the advent of the perceptron and consequent artificial neural networks, developed using local properties of individual neurons. We wish to continue this trend by studying the network processing of ensembles of living neurons that lead to higher-level cognition and intelligent behavior.
Summary. We present a kinodynamic planning methodology for a high-impedance quadruped robot to negotiate a wide variety of terrain types with high reliability. We achieve motion types ranging from dynamic, double-support lunges for efficient locomotion over extreme obstacles to careful, deliberate foothold and body pose selections which allow for precise foothold placement on rough or intermittent terrain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.