Motion planning

About: Motion planning is a research topic. Over the lifetime, 32846 publications have been published within this topic receiving 553548 citations.

An Autonomous Path Planning Model for Unmanned Ships Based on Deep Reinforcement Learning

Abstract: Deep reinforcement learning (DRL) has excellent performance in continuous control problems and it is widely used in path planning and other fields. An autonomous path planning model based on DRL is proposed to realize the intelligent path planning of unmanned ships in the unknown environment. The model utilizes the deep deterministic policy gradient (DDPG) algorithm, through the continuous interaction with the environment and the use of historical experience data; the agent learns the optimal action strategy in a simulation environment. The navigation rules and the ship's encounter situation are transformed into a navigation restricted area, so as to achieve the purpose of planned path safety in order to ensure the validity and accuracy of the model. Ship data provided by ship automatic identification system (AIS) are used to train this path planning model. Subsequently, the improved DRL is obtained by combining DDPG with the artificial potential field. Finally, the path planning model is integrated into the electronic chart platform for experiments. Through the establishment of comparative experiments, the results show that the improved model can achieve autonomous path planning, and it has good convergence speed and stability.

A binary paradigm for robotic manipulators

Abstract: Traditionally, kinematics and motion planning paradigms have addressed robots with continuous range-of-motion actuators (e.g. motors, hydraulic cylinders, etc.). Unlike motors, binary actuators have only two discrete states, both of which are stable. As a result, binary manipulators (i.e. those which are actuated with binary actuators) have a finite number of states. Major benefits of binary actuation are that extensive feedback control is not required, task repeatability can be very high, and two-state actuators are generally very inexpensive (e.g. solenoids, pneumatic cylinders, etc.), thus resulting in low cost robots. This paper presents a new paradigm in robotics based on binary actuation, and develops algorithms for the optimal design of binary manipulators for pick-and-place tasks. >

Occupancy grid models for robot mapping in changing environments

Abstract: The majority of existing approaches to mobile robot mapping assumes that the world is static, which is generally not justified in real-world applications. However, in many navigation tasks including trajectory planning, surveillance, and coverage, accurate maps are essential for the effective behavior of the robot. In this paper we present a probabilistic grid-based approach for modeling changing environments. Our method represents both, the occupancy and its changes in the corresponding area where the dynamics are characterized by the state transition probabilities of a Hidden Markov Model. We apply an offline and an online technique to learn the parameters from observed data. The advantage of the online approach is that it can dynamically adapt the parameters and at the same time does not require storing the complete observation sequences. Experimental results obtained with data acquired by real robots demonstrate that our model is well-suited for representing changing environments. Further results show that our technique can be used to substantially improve the effectiveness of path planning procedures.

Mobile robot navigation in 2-D dynamic environments using an electrostatic potential field

Abstract: Proposes a solution to the two-dimensional (2-D) collision fee path planning problem for an autonomous mobile robot utilizing an electrostatic potential field (EPF) developed through a resistor network, derived to represent the environment. No assumptions are made about the amount of information contained in the a priori environment map (it may be completely empty) or the shape of the obstacles. The well-formulated and well-known laws of electrostatic fields are used to prove that the proposed approach generates an approximately optimal path (based on cell resolution) in a real-time frame. It is also proven through the classical laws of electrostatics that the derived potential function is a global navigation function (as defined by Rimon and Koditschek, 1992), that the field is free of all local minima and that all paths necessarily lead to the goal position. The complexity of the EPF generated path is shown to be O(mn/sub M/), where m is the total number of polygons in the environment and n/sub M/ is the maximum number of sides of a polygonal object. The method is tested both by simulation and experimentally on a Nomad200 mobile robot platform equipped with a ring of sixteen sonar sensors.

Probabilistic roadmap methods are embarrassingly parallel

Abstract: In this paper we report on our experience in parallelizing probabilistic roadmap motion planning methods (PRMs). We show that significant, scalable speed-ups can be obtained with relatively little effort on the part of the developer. Our experience is not limited to PRMs. In particular, we outline general techniques for parallelizing types of computations commonly performed in motion planning algorithms, and identify potential difficulties that might be faced in other efforts to parallelize sequential motion planning methods.