Feature-Based Occupancy Map-Merging for Collaborative SLAM

Abstract

One of the most frequently used approaches to represent collaborative mapping are probabilistic occupancy grid maps. These maps can be exchanged and integrated among robots to reduce the overall exploration time, which is the main advantage of the collaborative systems. Such map fusion requires solving the unknown initial correspondence problem. This article presents an effective feature-based map fusion approach that includes processing the spatial occupancy probabilities and detecting features based on locally adaptive nonlinear diffusion filtering. We also present a procedure to verify and accept the correct transformation to avoid ambiguous map merging. Further, a global grid fusion strategy based on the Bayesian inference, which is independent of the order of merging, is also provided. It is shown that the presented method is suitable for identifying geometrically consistent features across various mapping conditions, such as low overlapping and different grid resolutions. We also present the results based on hierarchical map fusion to merge six individual maps at once in order to constrict a consistent global map for SLAM.

Enhancing Object Detection in Smart Video Surveillance: A Survey of Occlusion-Handling Approaches

“…This precision is achieved through the POM detector, which adeptly manages complex occlusion interactions among detected individuals. The detector employs an advanced generative model to estimate the probability of occupancy [49].…”

Single-Line LiDAR Localization via Contribution Sampling and Map Update Technology

“…To address the map update issue for multiple robots, Ref. [ 25 ] proposed a global grid fusion strategy based on Bayesian inference, which is independent of the order of merging. This method requires multiple vehicles to operate collaboratively and does not solve map change problems encountered by a single vehicle.…”

LSTM-based Preceding Vehicle Behaviour Prediction during Aggressive Lane Change for ACC Application

“…The utilization of MPC in ACC systems offers several advantages, including its ability to achieve precise and optimal control, real-time multi-objective optimal control, and even high responsiveness during traffic congestion [8]. Deep learning has become a prominent focus of research in numerous systems and applications in recent years and has been used in various transportation and autonomous driving applications such as ACC systems [9,10], cooperative adaptive cruise control (CACC) [11], traffic sign recognition [12], and map merging [13]. As per the author's knowledge, there was no use of the real-world data set in the above literature for developing the models.…”