Learning Metric-Topological Maps for Indoor Mobile Robot Navigation

By Sebastian Thrun. 1998

How researchers see this paper

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

Citations in the corpus

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, positive): “r than human demonstrations. Understanding the world is central to planning, control and (model-based) RL. In robotics, one often needs to locate or navigate itself by interpreting a map of the world [61, 87, 3]. Our exploration strategy borrows the high-level insight from robotics active localizati”
Graying the black box: Understanding DQNs (2016, methodology): “In this work we analyze the representation of states learned by DRL agents.”
Semi-parametric Topological Memory for Navigation (2018, methodology): “Models based on topological maps have been applied to navigation in simple 2D mazes (Kuipers & Byun, 1991; Meng & Kak, 1993; Sch¨olkopf & Mallot, 1995) and on physical systems (Hong et al., 1992; Bachelder & Waxman, 1995; Franz et al., 1998; Thrun, 1998; Fraundorfer et al., 2007).”
Probabilistic Algorithms and the Interactive Museum Tour-Guide Robot Minerva (2000, methodology): “Occupancy grids are widely used in mobile robotics (see, e.g., Borenstein 1987; Elfes 1987; Guzzoni et al. 1997; Thrun 1998b; Yamauchi and Langley 1997).”
Semantic mapping for mobile robotics tasks: A survey (2015, background): “Besides, topological mapping involves a graph, each of the nodes of which corresponds to a distinguished place in the real environment [22], [23], such as the maps of the subway placed above the wagon doors.”
A Survey and Analysis of Multi-Robot Coordination (2013, unknown): “The strategy extracts the critical points [132] as the targets to assign them to the robots for task allocation.”
A Probabilistic Approach to Collaborative Multi-Robot Localization (2000, background): “, a map [66]), and tha t they re given sensors that enable them to relate their own position to this model (e.”
Predictive Robot Programming: Theoretical and Experimental Analysis (2004, background): “If the user repeats a task with a slight difference in orientation, then the Cartesian errors between the two demonstrations can quickly accumulate and become large, similar to the compounding of dead-reckoning errors in a mobile robot (Thrun 1998).”
A survey on coverage path planning for robotics (2013, background): “Nonetheless, grid maps suffer from exponential growth of memory usage because the resolution remains constant regardless of the complexity of the environment (Thrun, 1998).”
A Gesture Based Interface for Human-Robot Interaction (2000, methodology): “The robot then uses its visual routines Margaritis and Thrun, 1998 to determine the exact location of the soda can.”
Biomimetic robot navigation (2000, unknown): “Therefore, many recent approaches are topological, or construct a topological representation from a global map (e.g., [ 74 ]).”
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning (2018, background): “Traditional navigation methods typically perform planning on a given map of the environment or build a map as the exploration proceeds [26, 40, 21, 24, 9, 4].”
Mobile Robot Localisation and Mapping in Extensive Outdoor Environments (2002, methodology): “Thus, the two grids do not overlap cleanly and interpolation techniques are required, as shown in [128] for example.”
6D SLAM—3D mapping outdoor environments (2007, background): “report a time of about one week hard work for creating a map of the museum in Bonn for the robot RHINO [19].”
Visual Navigation for Mobile Robots: A Survey (2008, background): “Thrun [137] went one step further with a remarkable contribution, combining the best of occupancy grids and topological maps for navigation.”
Learning Occupancy Grid Maps with Forward Sensor Models (2003, unknown): “Various authors have investigated building such maps while simultaneously localizing the robot (Burgard, 1999; Thrun, 1998; Yamauchi et al., 1998) and during robot exploration (Burgard, 2000; Simmons et al., 2000; Thrun, 1993; Yamauchi, 1997).”