公开(公告)号：US11409296B1

公开(公告)日：2022-08-09

申请号：US16573845

申请日：2019-09-17

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Chang Young Kim ,  Roger Robert Webster

IPC: G05D1/02 ,  G05D1/00 ,  G06V20/10

Abstract: An autonomous mobile device (AMD) moves through a physical space without human intervention. Data from sensors on the AMD is used to determine an occupancy map indicative of obstacles and their locations in the physical space. Obstacles may be static, variable, or dynamic. For example, walls are static, doors which open and close are variable, and people moving through the environment are dynamic. Regions in the occupancy map that the AMD has visited but which are shown by the occupancy map as containing obstacles are identified as being variable regions. To determine possible paths through the physical space during autonomous movement, the variable regions are considered to be unoccupied by obstacles and traversable. Information about how often the variable region transitions between traversable and impassible states may also be used to determine the possible paths.

公开(公告)号：US11720117B1

公开(公告)日：2023-08-08

申请号：US17082988

申请日：2020-10-28

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Chang Young Kim ,  Shashikanth Sreenivasaiah ,  Stephen Phillips

IPC: G05D1/02

CPC classification number: G05D1/0238 ,  G05D1/0212 ,  G05D1/0274 ,  G05D2201/0207

Abstract: An autonomous mobile device (AMD) uses sensors to explore a physical space and determine the locations of obstacles. Simultaneous localization and mapping (SLAM) techniques are used to process images from cameras to determine location and trajectory of the device. As the AMD moves and explores to generate an occupancy map, errors in the localization accrue. The occupancy map is processed to determine a graph that is based on, for a given point in physical space, a distance, relative direction, and a characteristic of a closest obstacle. A first graph based on a global occupancy map may be compared to a second graph based on a local occupancy map to determine a displacement between the local occupancy map and the global occupancy map. To facilitate loop closure, the AMD may navigate to a point along the first graph, where a loop closure process may be performed.

公开(公告)号：US11520332B1

公开(公告)日：2022-12-06

申请号：US16702008

申请日：2019-12-03

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： James Charles Zamiska ,  David Allen Fotland ,  Roger Robert Webster ,  Mohit Deshpande ,  Robert Franklin Ebert ,  Nikhil Sharma ,  Rachel Liao ,  Chang Young Kim

IPC: G05D1/00 ,  G01S17/931 ,  G05D1/02

Abstract: An autonomous mobile device (AMD) uses sensors to explore a physical space and determine the locations of obstacles. Simultaneous localization and mapping (SLAM) techniques are used by the AMD to designate as keyframes some images and their associated descriptors of features in the space. Each keyframe indicates a location and orientation of the AMD relative to those features. Anchors are specified relative to keyframes. A marker is specified relative to one or more anchors. Because markers are associated with features in the physical space, they maintain their association with the physical space through various processes such as SLAM loop closures. Markers may specify locations in the physical space, such as navigation waypoints, navigation destinations such as a goal pose for exploring an unexplored area, as an observation target to facilitate exploration, and so forth. Markers may also be used to specify block listed locations to be avoided during exploration.

公开(公告)号：US11274930B1

公开(公告)日：2022-03-15

申请号：US16710935

申请日：2019-12-11

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： Rajasimman Madhivanan ,  Heidi Christine Schubert ,  Chang Young Kim ,  Madan Jayaprakasam ,  Madhav Achar

IPC: G01C21/32 ,  G01C21/30 ,  G01C21/20 ,  B60W60/00 ,  G05D1/00

Abstract: An autonomous mobile device (AMD) uses sensors to explore a physical space and determine a map indicating the locations of obstacles. As data is later acquired, the map may be updated, resulting in changes to previously mapped obstacle positions. Navigability tests determine if a path can be found between a current location and a previously visited location. A failure to find a path may result in exploration of an area that includes the previously visited location. Submaps may be produced by the AMD as it moves through the physical space. An accuracy score of a selected submap is determined by comparing the selected submap with a partial global map created using submaps other than the selected submap. If the accuracy score is less than a threshold value, the selected submap may be discarded and an area in the physical space associated with the selected submap may be re-explored.