Geometric and Bayesian models for safe navigation in dynamic environments

Autonomous vehicles (AVs) are considered an emerging technology revolution. Planning paths that are safe to drive on contributes greatly to expediting AV adoption. However, the main barrier to this adoption is navigation under sensor uncertainty, with the understanding that there is no perfect sensing solution for all driving environments. In this paper, we propose a global safe path planner that analyzes sensor uncertainty and determines optimal paths. The path planner has two components: sensor analytics and path finder. The sensor analytics component combines the uncertainties of all sensors to evaluate the positioning and navigation performance of an AV at given locations and times. The path finder component then utilizes the acquired sensor performance and creates a weight based on safety for each road segment. The operation and quality of the proposed path finder are demonstrated through simulations. The simulation results reveal that the proposed safe path planner generates paths that significantly improve the navigation safety in complex dynamic environments when compared to the paths generated by conventional approaches.

Download Full-text

Safe Navigation in Dynamic Environments

ROMANSY 18 Robot Design, Dynamics and Control - CISM International Centre for Mechanical Sciences ◽

10.1007/978-3-7091-0277-0_26 ◽

2010 ◽

pp. 225-232 ◽

Cited By ~ 1

Author(s):

Zvi Shiller ◽

Oren Gal ◽

Elon Rimon

Keyword(s):

Dynamic Environments ◽

Safe Navigation

Download Full-text

A Hybrid Approach for Autonomous Collision-Free UAV Navigation in 3D Partially Unknown Dynamic Environments

Drones ◽

10.3390/drones5030057 ◽

2021 ◽

Vol 5 (3) ◽

pp. 57

Author(s):

Taha Elmokadem ◽

Andrey V. Savkin

Keyword(s):

Sliding Mode ◽

Hybrid Approach ◽

Three Dimensional ◽

Dynamic Environments ◽

Reactive Control ◽

Suggested Approach ◽

Safe Navigation ◽

Wide Range ◽

Planning Algorithm ◽

Path Planning Algorithm

In the past decades, unmanned aerial vehicles (UAVs) have emerged in a wide range of applications. Owing to the advances in UAV technologies related to sensing, computing, power, etc., it has become possible to carry out missions autonomously. A key component to achieving this goal is the development of safe navigation methods, which is the main focus of this work. A hybrid navigation approach is proposed to allow safe autonomous operations in three-dimensional (3D) partially unknown and dynamic environments. This method combines a global path planning algorithm, namely RRT-Connect, with a reactive control law based on sliding mode control to provide quick reflex-like reactions to newly detected obstacles. The performance of the suggested approach is validated using simulations.

Download Full-text

Safe Navigation in Unknown Dynamic Environments with Voronoi Based StRRT

2008 IEEE/SICE International Symposium on System Integration ◽

10.1109/si.2008.4770427 ◽

2008 ◽

Cited By ~ 4

Author(s):

Hiroto Sakahara ◽

Yasuhiro Masutani ◽

Fumio Miyazaki

Keyword(s):

Dynamic Environments ◽

Safe Navigation

Download Full-text

Provably safe navigation for mobile robots with limited field-of-views in dynamic environments

Autonomous Robots ◽

10.1007/s10514-011-9258-8 ◽

2011 ◽

Vol 32 (3) ◽

pp. 267-283 ◽

Cited By ~ 52

Author(s):

Sara Bouraine ◽

Thierry Fraichard ◽

Hassen Salhi

Keyword(s):

Mobile Robots ◽

Dynamic Environments ◽

Safe Navigation

Download Full-text

Real-Time Safe Navigation in Crowded Dynamic Environments Using Generalized Velocity Obstacles

Volume 5B: 38th Mechanisms and Robotics Conference ◽

10.1115/detc2014-35036 ◽

2014 ◽

Author(s):

Mostafa Mahmoodi ◽

Khalil Alipour ◽

Mehdi Tale Masouleh ◽

Hadi Beik Mohammadi

Keyword(s):

Path Planning ◽

Real Time ◽

Time Horizon ◽

Dynamic Environments ◽

Local Motion ◽

Safe Navigation ◽

Changing Environments ◽

Wide Range ◽

Planning Problems ◽

Navigation Method

This paper aims at developing a real-time, robust, and reliable navigation method for an omnidirectional robot, the so-called MRL-SSL RoboCup robot, can be used in crowded dynamically-changing environments. To this end, a local motion planner will be introduced which combining the Generalized Velocity Obstacles (GVO) notion and a heuristic approach for determining the time horizon such that the inevitable collision states can successfully be avoided. The proposed method considers not only the kinematics of the robot but also its dynamics. Moreover, it could be extended to a wide range of practical path planning problems containing uncertainties. Finally, in order to demonstrate the performance and effectiveness of the proposed motion planner for the omnimobile robots, some practical scenarios are simulated.

Download Full-text