Probabilistic traversability map generation using 3D-LIDAR and camera

Sock, Juil; Kim, Jun; Min, June Kee; Kwak, Kiho

doi:10.1109/icra.2016.7487782

Cited by 51 publications

(38 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mean that the ground vehicles should perceive its surrounding environment during the autonomous platooning. In order for that, this study employs a traversability estimation algorithm with multiple sensors‐based probabilistic fusion scheme (Sock et al, 2016).…”

Section: Resultsmentioning

confidence: 99%

“…Traversability map around the ground vehicle (Sock et al, 2016) [Color figure can be viewed at wileyonlinelibrary.com]…”

Section: Resultsmentioning

confidence: 99%

“…The platooning algorithm is comprised of three main components: perception, planning, and control. While the perception component is developed using the method in Sock et al (2016) and the control system is obtained by the automobile company (Hyundai Rotem), the planning component is concentrated in this study.…”

Section: Overview Of Platooning In Rough Terrainmentioning

confidence: 99%

“…The dynamic and kinematic models of the ground vehicle are included as equality constraints, and limited range of states and control input are considered as inequality constraints. To generate the path only in traversable region, perception result about the vehicle's own neighborhood (Sock, Kim, Min, & Kwak, 2016) is employed and included in the cost function. Its solution is obtained using the particle swarm optimization (PSO) method (Kennedy & Eberhart, 1995).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Autonomous platooning of multiple ground vehicles in rough terrain

Shin

Kwak

Kim

2020

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

This study proposes an autonomous platooning algorithm, composed of velocity, and path planning systems, of multiple ground vehicles in rough terrain. The velocity planning system aims to maintain desired distance between preceding and rear vehicles, and the path planning system generates reliable path to make the vehicles move safely under the given rough environment. To supply a reliable velocity command for the maintenance of the predefined distance, a disturbance observer (DOB)‐based control method is employed. An uncertainty‐free longitudinal kinematic model is first utilized for a nominal velocity generator and the DOB is added to the nominal velocity planner for handling various uncertainties generated during the autonomous platooning. On the other hand, the path planning method is developed by employing a passivity‐based model predictive control method. With a derived passivity constraint, the stability of the platooning architecture, that is, the platooning performance, is improved. In addition, the proposed path planning method utilizes dynamic and kinematic models of the ground vehicle as equality constraints, and limited range of states and control input as inequality constraints, and perception result about the vehicle's own neighborhood is employed for generation of the path only in traversable region. Its solution is obtained using the particle swarm optimization method. Then, to follow the generated velocity and path commands, a well developed driving controller, commercially obtainable, is utilized. Finally, field tests are conducted to validate the performance of the proposed algorithm.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Traversability map around the ground vehicle (Sock et al, 2016) [Color figure can be viewed at wileyonlinelibrary.com]…”

Section: Resultsmentioning

confidence: 99%

Section: Overview Of Platooning In Rough Terrainmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Autonomous platooning of multiple ground vehicles in rough terrain

Shin

Kwak

Kim

2020

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the work by Sock et al [ 48 ] two probabilistic maps are independently built from RGB camera images and 3D LIDAR scans and combined through Bayesian fusion. A linear SVM classifier is chosen to binary classify RGB images depending on a set of visual features.…”

Section: Terrain Traversability Analysismentioning

confidence: 99%

Learning-Based Methods of Perception and Navigation for Ground Vehicles in Unstructured Environments: A Review

Guastella

Muscato

2020

Sensors

View full text Add to dashboard Cite

The problem of autonomous navigation of a ground vehicle in unstructured environments is both challenging and crucial for the deployment of this type of vehicle in real-world applications. Several well-established communities in robotics research deal with these scenarios such as search and rescue robotics, planetary exploration, and agricultural robotics. Perception plays a crucial role in this context, since it provides the necessary information to make the vehicle aware of its own status and its surrounding environment. We present a review on the recent contributions in the robotics literature adopting learning-based methods to solve the problem of environment perception and interpretation with the final aim of the autonomous context-aware navigation of ground vehicles in unstructured environments. To the best of our knowledge, this is the first work providing such a review in this context.

show abstract

Terrain‐aware path planning via semantic segmentation and uncertainty rejection filter with adversarial noise for mobile robots

Lee,

Lee

2024

Journal of Field Robotics

View full text Add to dashboard Cite

In ground mobile robots, effective path planning relies on their ability to assess the types and conditions of the surrounding terrains. Neural network‐based methods, which primarily use visual images for terrain classification, are commonly employed for this purpose. However, the reliability of these models can vary due to inherent discrepancies between the training images and the actual environment, leading to erroneous classifications and operational failures. Retraining models with additional images from the actual operating environment may enhance performance, but obtaining these images is often impractical or impossible. Moreover, retraining requires substantial offline processing, which cannot be performed online by the robot within an embedded processor. To address this issue, this paper proposes a neural network‐based terrain classification model, trained using an existing data set, with a novel uncertainty rejection filter (URF) for terrain‐aware path planning of mobile robots operating in unknown environments. A robot, equipped with a pretrained model, initially collects a small number of images (10 in this work) from its current environment to set the target uncertainty ratio of the URF. The URF then dynamically adjusts its sensitivity parameters to identify uncertain regions and assign associated traversal costs. This process occurs entirely online, without the need for offline procedures. The presented method was evaluated through simulations and physical experiments, comparing the point‐to‐point trajectories of a mobile robot equipped with (1) the neural network‐based terrain classification model combined with the presented adaptive URF, (2) the classification model without the URF, and (3) the classification model combined with a nonadaptive version of the URF. Path planning performance measured the Hausdorff distances between the desired and actual trajectories and revealed that the adaptive URF significantly improved performance in both simulations and physical experiments (conducted 10 times for each setting). Statistical analysis via t‐tests confirmed the significance of these results.

show abstract

Probabilistic traversability map generation using 3D-LIDAR and camera

Cited by 51 publications

References 22 publications

Autonomous platooning of multiple ground vehicles in rough terrain

Autonomous platooning of multiple ground vehicles in rough terrain

Learning-Based Methods of Perception and Navigation for Ground Vehicles in Unstructured Environments: A Review

Terrain‐aware path planning via semantic segmentation and uncertainty rejection filter with adversarial noise for mobile robots

Contact Info

Product

Resources

About