DEM-AIA: Asymmetric inclination-aware trajectory planner for off-road vehicles with digital elevation models

Toscano-Moreno, Manuel; Mandow, Anthony; Martínez, M.a Dolores Barrios; García-Cerezo, Alfonso

doi:10.1016/j.engappai.2023.105976

Cited by 12 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They then combine the A* algorithm with Q-Learning to achieve wheeled robot path planning. Martinez et al [19] propose a new ground vehicle non-symmetric inclination perception (DEM-AIA) trajectory planner based on DEM, enabling UGV to calculate slope-planned safe and viable trajectories on uneven terrain. Chen et al [20] convert DEM into a three-dimensional point cloud to generate a terrain model for path planning.…”

Section: Related Workmentioning

confidence: 99%

3D path planning of unmanned ground vehicles based on improved DDQN

Tang,

Peng,

Xie

et al. 2024

Preprint

View full text Add to dashboard Cite

For safe and efficient path planning of unmanned ground vehicles in complex 3D environment, this paper proposes an improved deep reinforcement learning algorithm (Dual Experience Dynamic Target DDQN, DEDT DDQN) to solve the problems of sparse reward convergence and over-estimation that are difficulties for traditional DDQN algorithms in complex maps. The algorithm improves the performance of the DDQN algorithm in dealing with complex environments by dividing the input quality experience and dynamically fusing the a priori knowledge of DDQN and average DDQN for network parameter training. For unstructured 3D environments, this paper adopts a path planning strategy based on the digital elevation model (DEM) considering environmental characteristics and time cost. Simulation experiments of the DEDT DDQN algorithm in 3D maps modeled on realistic environments show that the DEDT DDQN algorithm reduces the number of inflection points and the average slope change by 40% and 16.7%, respectively, and improves the performance of optimization searching as well as the convergence speed by 5.34% and 60%, respectively. The proposed improved algorithm and adopted strategy can be applied in two different types of maps, which verifies the effectiveness and robustness of the algorithm and strategy.

show abstract

Section: Related Workmentioning

confidence: 99%

3D path planning of unmanned ground vehicles based on improved DDQN

Tang,

Peng,

Xie

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Rover J8, developed by Argo (Kitchener, Ontario, Canada), is an electric off-road 8×8 UGV designed for outdoor navigation, with a weight of 1090 kg, and it has been modified by our Lab to include autonomous features [32]. Both UGVs are integrated as robotic agents in SAR-FIS, a management platform for distributed robotic systems in emergency missions, including path planning [33]. In addition, two human agents (from now on, HA1 and HA2) operated two smartphones (UE1 and UE2, respectively) while moving through the dual-tunnel.…”

Section: System Overviewmentioning

confidence: 99%

Field Report on Experimental Comparison of a WiFi Mesh Network Against Commercial 5G in an Underground Disaster Environment

Bravo-Arrabal,

Álvarez-Merino,

Fernandez-Lozano

et al. 2023

2023 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

Self Cite

View full text Add to dashboard Cite

Mobile robots in disaster scenarios such as tunnels, mines, or collapsed structures face communication challenges for reliable video streaming to remote control centers. Commercial fifth-generation (5G) networks provide low latency and high bandwidth, especially in urban areas, but ad hoc WiFi networks with static and robotic nodes can provide a solution to attenuation in occluded areas. This paper offers a field experiment report from a search and rescue (SAR) exercise where we tested a WiFi mesh network against commercial 5G in tunnels 184 m long, 6 m wide, and 4 m high. Two operator streamed video to the Internet through a mesh that consisted of two static nodes and two mobile nodes on unmanned ground vehicles (UGV). Latency was measured for both operators for different video resolutions, as well as for a 5G customer-premises equipment (CPE) on-board a scout-UGV. The paper discusses experimental results and lessons learned.

show abstract

“…Another objective can be generated if the robot must perform missions that require mapping over large spaces; the criterion can be determined through the management of the energy resource [21]. Otherwise, if the robot has to travel along a route with obstacles, a criterion can be the shortest path between two landmarks (obstacles) [22,23].…”

Section: Introductionmentioning

confidence: 99%

Optimizing an Autonomous Robot’s Path to Increase Movement Speed

Gorgoteanu,

Molder,

Popescu

et al. 2024

Electronics

View full text Add to dashboard Cite

The goal of this study is to address the challenges associated with identifying and planning a mobile land robot’s path to optimize its speed in a stationary environment. Our focus was on devising routes that navigate around obstacles in various spatial arrangements. To achieve this, we employed MATLAB R2023b for trajectory simulation and optimization. On-board data processing was conducted, while obstacle detection relied on the omnidirectional video processing system integrated into the robot. Odometry was facilitated by engine encoders and optical flow sensors. Additionally, an external video system was utilized to verify the experimental data pertaining to the robot’s movement. Last but not least, the algorithms and hardware equipment used enabled the robot to go along the path at greater speeds. Limiting the amount of time and energy required to travel allowed us to avoid obstacles.

show abstract

DEM-AIA: Asymmetric inclination-aware trajectory planner for off-road vehicles with digital elevation models

Cited by 12 publications

References 34 publications

3D path planning of unmanned ground vehicles based on improved DDQN

3D path planning of unmanned ground vehicles based on improved DDQN

Field Report on Experimental Comparison of a WiFi Mesh Network Against Commercial 5G in an Underground Disaster Environment

Optimizing an Autonomous Robot’s Path to Increase Movement Speed

Contact Info

Product

Resources

About