2D SLAM quality evaluation methods

Filatov, Antón; Filatov, Artyom; Krinkin, Kirill; Chen, Baian; Molodan, Diana

doi:10.23919/fruct.2017.8250173

Cited by 29 publications

(21 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though there are many excellent works on evaluation of the 2D LiDAR SLAM, such as the references [44][45][46][47], to name a few, and some open datasets for the evaluation are presented, we found that, because the ground truth is limited, and many datasets recorded only one sensor, some differences of the input data format make the dataset not able to run on all state-of-the-art methods. All these factors make the evaluation still a challenging work.…”

Section: Discussionmentioning

confidence: 99%

“…There are some state-of-the-art 2D LiDAR-based SLAM methods, such as Hector SLAM [7], GMapping [10], KartoSLAM [41], CoreSLAM [42], LagoSLAM [43], and Cartographer [40], which have been proposed, and some papers on the performance evaluation are published [44][45][46][47]. As mentioned in reference [44], among the former five methods (Cartographer was proposed later), KartoSLAM, GMapping, and HectorSLAM show better performance than the other two methods. Both KartoSLAM and LagoSLAM are graph-based optimizations, but the computation load of LagoSLAM is higher than that of KartoSLAM.…”

Section: The Platformmentioning

confidence: 99%

“…All these factors make the comparison a little hard. In this paper, we apply the proportion of occupied and free cells to the quantitative comparison, which has been proposed in reference [44] for quality evaluation. As shown in Figure 6, the perceptible feature of the picture of a map is the accuracy of the walls or edges.…”

Section: The Platformmentioning

confidence: 99%

See 2 more Smart Citations

IMU-Assisted 2D SLAM Method for Low-Texture and Dynamic Environments

et al. 2018

View full text Add to dashboard Cite

Generally, the key issues of 2D LiDAR-based simultaneous localization and mapping (SLAM) for indoor application include data association (DA) and closed-loop detection. Particularly, a low-texture environment, which refers to no obvious changes between two consecutive scanning outputs, with moving objects existing in the environment will bring great challenges on DA and the closed-loop detection, and the accuracy and consistency of SLAM may be badly affected. There is not much literature that addresses this issue. In this paper, a mapping strategy is firstly exploited to improve the performance of the 2D SLAM in dynamic environments. Secondly, a fusion method which combines the IMU sensor with a 2D LiDAR, based on framework of extended Kalman Filter (EKF), is proposed to enhance the performance under low-texture environments. In the front-end of the proposed SLAM method, initial motion estimation is obtained from the output of EKF, and it can be taken as the initial pose for the scan matching problem. Then the scan matching problem can be optimized by the Levenberg–Marquardt (LM) algorithm. For the back-end optimization, a sparse pose adjustment (SPA) method is employed. To improve the accuracy, the grid map is updated with the bicubic interpolation method for derivative computing. With the improvements both in the DA process and the back-end optimization stage, the accuracy and consistency of SLAM results in low-texture environments is enhanced. Qualitative and quantitative experiments with open-loop and closed-loop cases have been conducted and the results are analyzed, confirming that the proposed method is effective in low-texture and dynamic indoor environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: The Platformmentioning

confidence: 99%

See 1 more Smart Citation

IMU-Assisted 2D SLAM Method for Low-Texture and Dynamic Environments

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In particular, our metrics are inspired to the ones designed in [3] to evaluate the maps generated by a SLAM algorithm running on a mobile agent, that are rather similar to the maps generated by our network. Note that, the proposed metrics are not meant to provide a general solution to the problem of evaluating samples of a GAN nor to improve previous work on the evaluation of maps generated by SLAM algorithms [3]. δE: we compute the entropy of the pixel distribution for all the images that represent both human-designed and generated levels.…”

Section: Levels Evaluationmentioning

confidence: 99%

DOOM Level Generation Using Generative Adversarial Networks

Giacomello

Lanzi

Loiacono

2018

2018 IEEE Games, Entertainment, Media Conference (GEM)

View full text Add to dashboard Cite

We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analyzed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of game objects. We trained two GANs: one using plain level images, one using both the images and some of the features extracted during the preliminary analysis. We used the two networks to generate new levels and compared the results to assess whether the network trained using also the topological features could generate levels more similar to human-designed ones. Our results show that GANs can capture intrinsic structure of DOOM levels and appears to be a promising approach to level generation in first person shooter games.

show abstract

“…An extensive literature exists on the more general problem of simultaneous localization and mapping (SLAM), where there are basically two approaches based on filtering or optimization methods, see the following surveys [ 2 , 3 , 4 , 5 , 6 ]. In [ 7 , 8 ], the authors proposed an efficient solution to implement Rao–Blackwellized particle filters to obtain occupancy grid maps of the environments.…”

Section: Introductionmentioning

confidence: 99%

LiDAR-Based GNSS Denied Localization for Autonomous Racing Cars

Massa

Bonamini

Settimi

et al. 2020

Sensors

View full text Add to dashboard Cite

Self driving vehicles promise to bring one of the greatest technological and social revolutions of the next decade for itstheir potential to drastically change human mobility and goods transportation, in particular regarding efficiency and safety. Autonomous racing provides very similar technological issues while allowing for more extreme conditions in a safe human environment. While the software stack driving the racing car consists of several modulessuch as sensor data processing, perception, mapping, localization, planning and control, in this paper we focus on the localization problem, which provides as output the estimated pose of the vehicle needed by the planning and control modules. When driving near the friction limits, localization accuracy is critical as small errors can induce large errors in control due to the nonlinearities of the vehicle’s dynamic model. Moreover, fast and accurate pose estimation is a necessary tool to tackle corners and negotiate overtakings along the path that minimizes lap time. In this paper, we present a localization architecture for a racing car that does not rely on Global Navigation Satellite Systems (GNSS). It consists consistingof two multi-rate Extended Kalman Filters and an extension of the classicala state-of-the-art laser-based Monte Carlo localization approach that exploits some a priori knowledge of the environment and context. We first compare the proposed method with a solution based on a widely employed state-of-the-art implementation, outlining its strengths and limitations within our experimental scenario. The architecture is then tested both in simulation and experimentally on a full-scale autonomous electric racing car during an event of Roborace Season Alpha. The results show its robustness in avoiding the robot kidnapping problem typical of particle filters localization methods, while providing a smooth and high rate pose estimate. The pose error distribution depends on the car velocity, and spans on average from 0.1 m (at 60 km/h) to 1.48 m (at 200 km/h) laterally and from 1.9 m (at 100 km/h) to 4.92 m (at 200 km/h) longitudinally.

show abstract

2D SLAM quality evaluation methods

Cited by 29 publications

References 17 publications

IMU-Assisted 2D SLAM Method for Low-Texture and Dynamic Environments

IMU-Assisted 2D SLAM Method for Low-Texture and Dynamic Environments

DOOM Level Generation Using Generative Adversarial Networks

LiDAR-Based GNSS Denied Localization for Autonomous Racing Cars

Contact Info

Product

Resources

About