Motion planning

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

Path Planning for Unmanned Aerial Vehicles in Uncertain and Adversarial Environments

Abstract: One of the main objectives when planning paths for unmanned aerial vehicles in adversarial environments is to arrive at the given target, while maximizing the safety of the vehicles. If one has perfect information of the threats that will be encountered, a safe path can always be constructed by solving an optimization problem. If there are uncertainties in the information, however, a different approach must be taken. In this paper we propose a path planning algorithm based on a map of the probability of threats, which can be built from a priori surveillance data. An extension to this algorithm for multiple vehicles is also described, and simulation results are provided.

Survey of Motion Planning Literature in the Presence of Uncertainty: Considerations for UAV Guidance

Abstract: This paper provides a survey of motion planning techniques under uncertainty with a focus on their application to autonomous guidance of unmanned aerial vehicles (UAVs). The paper first describes the primary sources of uncertainty arising in UAV guidance and then describes relevant practical techniques that have been reported in the literature. The paper makes a point of distinguishing between contributions from the field of robotics and artificial intelligence, and the field of dynamical systems and controls. Mutual and individual contributions for these fields are highlighted providing a roadmap for tackling the UAV guidance problem.

Fast Genetic Algorithm Path Planner for Fixed-Wing Military UAV Using GPU

Abstract: Military unmanned aerial vehicles (UAVs) are employed in highly dynamic environments and must often adjust their trajectories based on the evolving situation. To operate autonomously and safely, a UAV must be equipped with a path planning module capable of quickly recalculating a feasible and quasi-optimal path in flight while in the event a new obstacle or threat has been detected or simply if the destination point is changed during the mission. To allow for a fast path planning, this paper proposes a parallel implementation of the genetic algorithm on graphics processing unit (GPU). The trajectories are built as series of line segments connected by circular arcs resulting in smooth paths suitable for fixed-wing UAVs. The fitness function we defined takes into account the dynamic constraints of the UAVs and aims to minimize fuel consumption and average flying altitude in order to improve range and avoid detection by enemy radars. This fitness function is also implemented on the GPU and different parallelization strategies were developed and tested for each step of the fitness evaluation. By exploiting the massively parallel architecture of GPUs, the execution time of the proposed path planner was reduced by a factor of 290x compared to a sequential execution on CPU. The path planning module developed was tested using 18 scenarios on six realistic three-dimensional terrains with multiple no-fly zones. We found that the proposed GPU-based path planner was able to find quasi-optimal solutions in a timely fashion allowing in-flight planning.

Toward a Unified Bayesian Approach to Hybrid Metric--Topological SLAM

Abstract: This paper introduces a new approach to simultaneous localization and mapping (SLAM) that pursues robustness and accuracy in large-scale environments. Like most successful works on SLAM, we use Bayesian filtering to provide a probabilistic estimation that can cope with uncertainty in the measurements, the robot pose, and the map. Our approach is based on the reconstruction of the robot path in a hybrid discrete-continuous state space, which naturally combines metric and topological maps. There are two fundamental characteristics that set this paper apart from previous ones: 1) the use of a unified Bayesian inference approach both for the metrical and the topological parts of the problem and 2) the analytical formulation of belief distributions over hybrid maps, which allows us to maintain the spatial uncertainty in large spaces more accurately and efficiently than in previous works. We also describe a practical implementation that aims for real-time operation. Our ideas have been validated by promising experimental results in large environments (up to 30 000 m2, a 2 km robot path) with multiple nested loops, which could hardly be managed appropriately by other approaches.

Learning objective functions for manipulation

Abstract: We present an approach to learning objective functions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning algorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the resulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization-based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.