A Real-Time 3D Path Planning Solution for Collision-Free Navigation of Multirotor Aerial Robots in Dynamic Environments

Sánchez-López, José Luis; Wang, Min; Olivares-Méndez, Miguel A.; Molina, Martín; Voos, Holger

doi:10.1007/s10846-018-0809-5

Cited by 73 publications

(37 citation statements)

References 41 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Iyer et al [ 27 ] proposed an approach of collision avoidance robotics via meta-learning (CARML) to explore a 2D vehicle navigation equipped with a lidar sensor and compare against a baseline TD3 solution to solve the same problem. Sánchez-López et al [ 28 ] presented a real-time 3D path planning solution for multi-rotor aerial robots, where a probabilistic graph is utilized to sample the admissible space without taking into account the existing obstacles and the generated probabilistic graph is then explored by an A* discrete search algorithm with an artificial field map as cost function in order to obtain a raw optimal collision-free path. Kim et al [ 29 ] designed a motion planning algorithm using TD3 with hindsight experience replay to enhance sample efficiency, where the designed paths are smoother and shorter than those designed by PRM.…”

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning for Indoor Mobile Robot Path Planning

Gao

Guo

et al. 2020

Sensors

110

View full text Add to dashboard Cite

This paper proposes a novel incremental training mode to address the problem of Deep Reinforcement Learning (DRL) based path planning for a mobile robot. Firstly, we evaluate the related graphic search algorithms and Reinforcement Learning (RL) algorithms in a lightweight 2D environment. Then, we design the algorithm based on DRL, including observation states, reward function, network structure as well as parameters optimization, in a 2D environment to circumvent the time-consuming works for a 3D environment. We transfer the designed algorithm to a simple 3D environment for retraining to obtain the converged network parameters, including the weights and biases of deep neural network (DNN), etc. Using these parameters as initial values, we continue to train the model in a complex 3D environment. To improve the generalization of the model in different scenes, we propose to combine the DRL algorithm Twin Delayed Deep Deterministic policy gradients (TD3) with the traditional global path planning algorithm Probabilistic Roadmap (PRM) as a novel path planner (PRM+TD3). Experimental results show that the incremental training mode can notably improve the development efficiency. Moreover, the PRM+TD3 path planner can effectively improve the generalization of the model.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning for Indoor Mobile Robot Path Planning

Gao

Guo

et al. 2020

Sensors

110

View full text Add to dashboard Cite

show abstract

“…Commonly used UAVs can be categorised as non-holonomic mobile robots [42] as the degree of their controllable actuators is less than their degree of freedom in the space which they operate; therefore, path planning optimisation adds further complexity in comparison to holonomic systems. In order to address such challenges, researchers divide path planning into two main subsystems; a global path planning subsystem complemented by a lower level addressing collision avoidance.…”

Section: State Of the Artmentioning

confidence: 99%

Internet of Unmanned Aerial Vehicles—A Multilayer Low-Altitude Airspace Model for Distributed UAV Traffic Management

Labib

Danoy

Musiał

et al. 2019

Sensors

View full text Add to dashboard Cite

The rapid adoption of Internet of Things (IoT) has encouraged the integration of new connected devices such as Unmanned Aerial Vehicles (UAVs) to the ubiquitous network. UAVs promise a pragmatic solution to the limitations of existing terrestrial IoT infrastructure as well as bring new means of delivering IoT services through a wide range of applications. Owning to their potential, UAVs are expected to soon dominate the low-altitude airspace over populated cities. This introduces new research challenges such as the safe management of UAVs operation under high traffic demands. This paper proposes a novel way of structuring the uncontrolled, low-altitude airspace, with the aim of addressing the complex problem of UAV traffic management at an abstract level. The work, hence, introduces a model of the airspace as a weighted multilayer network of nodes and airways and presents a set of experimental simulation results using three UAV traffic management heuristics.

show abstract

“…In this work we focus on planning feasible trajectories from given paths. These given paths might be provided by the user or by a geometric path planner such as [3], [7]. The maximum distance between the planned trajectories and the given paths must be bounded to avoid collisions with the obstacles of the environment, as a requirement for industrial oriented applications.…”

Section: A Motivationmentioning

confidence: 99%

Towards trajectory planning from a given path for multirotor aerial robots trajectory tracking

Sánchez-López

Olivares-Méndez

Castillo-Lopez

et al. 2018

2018 International Conference on Unmanned Aircraft Systems (ICUAS)

Self Cite

View full text Add to dashboard Cite

Planning feasible trajectories given desired collision-free paths is an essential capability of multirotor aerial robots that enables the trajectory tracking task, in contrast to path following. This paper presents a trajectory planner for multirotor aerial robots carefully designed considering the requirements of real applications such as aerial inspection or package delivery, unlike other research works that focus on aggressive maneuvering. Our planned trajectory is formed by a set of polynomials of two kinds, acceleration/deceleration and constant velocity. The trajectory planning is carried out by means of an optimization that minimizes the trajectory tracking time, applying some typical constraints as m-continuity or limits on velocity, acceleration and jerk, but also the maximum distance between the trajectory and the given path. Our trajectory planner has been tested in real flights with a big and heavy aerial platform such the one that would be used in a real operation. Our experiments demonstrate that the proposed trajectory planner is suitable for real applications and it is positively influencing the controller for the trajectory tracking task.

show abstract

A Real-Time 3D Path Planning Solution for Collision-Free Navigation of Multirotor Aerial Robots in Dynamic Environments

Cited by 73 publications

References 41 publications

Deep Reinforcement Learning for Indoor Mobile Robot Path Planning

Deep Reinforcement Learning for Indoor Mobile Robot Path Planning

Internet of Unmanned Aerial Vehicles—A Multilayer Low-Altitude Airspace Model for Distributed UAV Traffic Management

Towards trajectory planning from a given path for multirotor aerial robots trajectory tracking

Contact Info

Product

Resources

About