Long-term 3D map maintenance in dynamic environments

Abstract

International audienceNew applications of mobile robotics in dynamic urban areas require more than the single-session geometric maps that have dominated simultaneous localization and mapping (SLAM) research to date; maps must be updated as the environment changes and include a semantic layer (such as road network information) to aid motion planning in dynamic environments. We present an algorithm for long-term localization and mapping in real time using a three-dimensional (3D) laser scanner. The system infers the static or dynamic state of each 3D point in the environment based on repeated observations. The velocity of each dynamic point is estimated without requiring object models or explicit clustering of the points. At any time, the system is able to produce a most-likely representation of underlying static scene geometry. By storing the time history of velocities, we can infer the dominant motion patterns within the map. The result is an online mapping and localization system specifically designed to enable long-term autonomy within highly dynamic environments. We validate the approach using data collected around the campus of ETH Zurich over seven months and several kilometers of navigation. To the best of our knowledge, this is the first work to unify long-term map update with tracking of dynamic objects

Motion-based detection and tracking in 3D LiDAR scans

“…Model-free approaches are generally based on building a static map of the scene and using this map information for detecting dynamic objects. In [9], Pomerleau et al make a visibility assumption that the scene behind the object is observed, if an object moves. To leverage over this information, they compare an incoming scan with a global map and detect dynamic objects.…”

“…Proposed methods to solve this problem can be broadly subdivided into model-free [6], [9], [16] and model-based [8], [11], [10] approaches.…”

Autonomous Mission with a Mobile Manipulator—A Solution to the MBZIRC

“…This routine makes use of underlying iterative closest point (ICP) based localization and mapping [14,15] and the ROS navigation stack 2 for path planning and following. The navigation is divided into two main phases, first locating the panel in an exploration phase and secondly positioning the robot relative to it.…”

SPENCER: A Socially Aware Service Robot for Passenger Guidance and Help in Busy Airports

“…This allows us to not only learn the average motion directions and speeds, but also the variations of speed. Thus, in contrast to Pomerleau et al (2014), who average velocities of neighboring points over consecutive frames, the T-CTMap represents a complete distribution of velocities. …”