Vision for Mobile Robot Navigation: A Survey

By Guilherme N. DeSouza, A. Kak. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

1,561 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/15a0b5ad64ef55d566213e9af57452651b6e5c6f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators (2019, background): “Interactive Navigation: While the literature on autonomous robot navigation is vast and pro-liﬁc [23, 24, 25], less attention has been paid to navigation problems that require interactions with the environment, what we call Interactive Navigation.”
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding (2018, neutral): “sis [2], [3] and robotics navigation [4], [5].”
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks (2019, methodology): “We apply SMT on a set of visual navigation tasks, which have a long history in computer vision and robotics [6, 10, 39].”
State-of-The-Art and Applications of 3D Imaging Sensors in Industry, Cultural Heritage, Medicine, and Criminal Investigation (2009, background): “3D urban modeling and object detection are typical applications [35–38].”
Semantic mapping for mobile robotics tasks: A survey (2015, background): “The first twenty years of vision-based robot navigation are surveyed in [10].”
A review of mobile robots: Concepts, methods, theoretical framework, and applications (2019, background): “By comparing the camera images taken during navigation with the prerecorded images, the robot is capable out of finding its location.100 For a survey on vision for mobile robot navigation, see DeSouza and Kak.101”
An in-Depth Survey of Visible Light Communication Based Positioning Systems (2016, methodology): “When a camera is used as the receiver, VLC based positioning might look similar to the vision based positioning [15–18] which has been developed in robot vision or augmented reality applications, for quite long time.”
Visual Navigation for Mobile Robots: A Survey (2008, background): “and outdoor categories, as DeSouza and Kak [28] did, this survey distinguishes between map-based and mapless navigation, since some navigation systems proposed for indoor could also be properly adapted to work in outdoor environments and vice versa.”
Sensing and Manipulating Built-for-Human Environments (2004, neutral): “There is a long history of mobile robots that use vision for navigation in builtfor-human environments.(33) In general, the common appearance and geometry of built-for-human environments has been used both implicitly and explicitly to help vision processing.”
Autonomous pedestrians (2005, background): “), as well as the pedestrian’s own current position within it (or localization, a fundamental problem in robotics [7]).”
Synthetic Data for Deep Learning (2019, background): “Possible applications include SLAM, motion planning, and motion for control for self-driving cars (urban navigation) [177, 346, 411, 435], unmanned aerial vehicles [11, 126, 305], and more; see also general surveys of computer vision for mobile robot navigation [68,142] and perception and control fo”
A Unified Framework for Multioriented Text Detection and Recognition (2014, methodology): “In this paper, we propose a uniﬁed framework, which takes text detection and recognition as a whole and performs both tasks in a single uniﬁed pipeline.”
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning (2018, background): “A related problem is visual servoing, where visual feedback is used to reach a goal configuration [14, 15, 16].”
Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “, 2016), robots navigation (DeSouza and Kak, 2002; Liu and Samarabandu, 2005a,b; Schulz et al., 2015), and industrial automation (Ham et al.”
CLIP on Wheels: Zero-Shot Object Navigation as Object Localization and Exploration (2022, background): “While these frameworks are used widely for different robotics applications [21], they are known to be fragile in the presence of uncertainty [41].”
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models (2022, background): “It becomes the classic object localization and navigation problem [6] (for navigation subgoals) or simply executing the specified interaction action with the right objects (for interaction subgoals).”
Algorithms for collision-free navigation of mobile robots in complex cluttered environments: a survey (2014, background): “[33, 63], employs the capability of the visual sensor”
Survey of optical indoor positioning systems (2011, background): “A comprehensive survey of older works can be found in DeSouza and Kak [2].”
Reinforcement learning in computer vision (2018, background): “Many decisions made by a robot are based on visual information (images) captured by robot’s visual systems (cameras) [1, 2, 36, 42] with the use of extracted visual features describing environment for a current task.”
A survey on vision-based UAV navigation (2018, background): “Considering the environment and prior information used in navigation, visual localization, and mapping systems can be roughly classified into three categories: mapless system, map-based system, and map-building system (Desouza and Kak 2002) (Figure 3).”