A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers

Abstract

Active Simultaneous Localization and Mapping (SLAM) is the problem of planning and controlling the motion of a robot to build the most accurate and complete model of the surrounding environment. Since the first foundational work in active perception appeared, more than three decades ago, this field has received increasing attention across different scientific communities. This has brought about many different approaches and formulations, and makes a review of the current trends necessary and extremely valuable for both new and experienced researchers. In this work, we survey the state-ofthe-art in active SLAM and take an in-depth look at the open challenges that still require attention to meet the needs of modern applications. After providing a historical perspective, we present a unified problem formulation and review the well-established modular solution scheme, which decouples the problem into three stages that identify, select, and execute potential navigation actions. We then analyze alternative approaches, including beliefspace planning and deep reinforcement learning techniques, and review related work on multi-robot coordination. The manuscript concludes with a discussion of new research directions, addressing reproducible research, active spatial perception, and practical applications, among other topics.

A review of visual SLAM for robotics: evolution, properties, and future applications

“…Choosing the right visual SLAM algorithm is crucial for building an effective SLAM system. With the continuous advancements in V-SLAM methodologies responding to diverse challenges, it is essential to navigate structured criteria to deploy and implement precise solutions ( Placed et al, 2023 ; Sousa et al, 2023 ). In the context of robotic systems, we provide important parameters.…”

“…It uses techniques such as computer vision to extract and match visual data for localization and mapping ( Zhang et al, 2020 ; Chung et al, 2023 ). It allows robots to map complex environments while performing tasks such as navigation in dynamic fields ( Placed et al, 2023 ; Khoyani and Amini 2023 ). It places a strong emphasis on accurate tracking of camera poses and estimating past trajectories of the robot during its work ( Nguyen et al, 2022 ; Awais and Henrich 2010 ).…”

Spatial and Temporal Hierarchy for Autonomous Navigation Using Active Inference in Minigrid Environment

“…accuracy (3) This equation describes the perception process over past and present observations, wherein minimising the variational free energy leads to the approximate posterior becoming increasingly aligned with the true posterior beliefs. Essentially, this means that the process involves forming beliefs about hidden states that offer a precise and concise explanation of observed outcomes while minimising complexity.…”

A tightly-coupled method of lidar-inertial based on complementary filtering

“…Simultaneous localization and mapping [1][2][3][4][5][6] (SLAM) is a method used for autonomous vehicles that lets robots build a map and localize vehicles in that map at the same time. SLAM algorithms allow the vehicle to map out unknown environments.…”

“…This phenomenon is more pronounced for lidars with a smaller field of view. (2) In the back-end optimization, the Gauss-Newton method is used to solve the constructed least squares problem [17,18]. In the process of data optimization, the solution of pose may fall into a local optimum.…”