Amazon Technologies, Inc.

Eric Foxlin

Rui Zhang

Duc Hongle Ngo

Gregory Turner Witmer

Marcel Colman Eric Stieber

Prakriti Chintalapoodi

Boshen Niu

Christopher Wells Fitzhugh

Li Huang

Catherine May Farmer

Simon Edwards-Parton

Lu Xia

James Ballantyne

Harish Annavajjala

Babak Hashemizadeh

Described herein is a system for improving navigation by detecting glass surfaces. For example, the system may build an occupancy map representing objects present in an environment. The system performs additional processing to input scan data in order to detect glass surfaces and distinguish these glass surfaces from other obstacles. As glass is only detected within a narrow range of angles and the number of returns are small compared to non-glass surfaces, the system may determine whether an obstacle represented in the input scan data is glass by calculating a maximum range of angles and a number of overlapping returns for the obstacle. For example, the system may identify glass surfaces by identifying objects that are only detected within a narrow range of angles and that have a low number of overlapping returns.

Glass detection using lidar

An autonomous mobile device (AMD) may move around a physical space while performing tasks. Sensor data is used to determine an occupancy map of the physical space. Some objects within the physical space may be difficult to detect because of characteristics that result in lower confidence in sensor data, such as transparent or reflective objects. To include difficult-to-detect objects in the occupancy map, image data is processed to identify portions of the image that includes features associated with difficult-to-detect objects. Given the portion that possibly includes difficult-to-detect objects, the AMD attempts to determine where in the physical space that portion corresponds to. For example, the AMD may use stereovision to determine the physical area associated with the features depicted in the portion. Objects in that area are included in an occupancy map annotated as objects that should persist unless confirmed to not be within the physical space.

System for object detection by an autonomous mobile device

An autonomous mobile device (AMD) in a physical space uses its own reflection to detect and map reflective surfaces. A first image is acquired by a camera of the AMD at a first time while a light on the AMD is turned on. The first image is processed to find a candidate reflection, characterized by a bright spot in the image. A second image is acquired at a second time while the light is off. The reflection is confirmed by absence of the candidate reflection in the second image. A display on the AMD presents a displayed image at a third time. A third image acquired during the third time is processed to find the features of the displayed image. Once found, a location and orientation in physical space of a plane of the surface causing the reflection is calculated. An occupancy map is updated to include this information.

System to detect and map reflective surfaces by autonomous mobile device

An autonomous mobile device (AMD) builds up electrostatic charges from moving and generates heat from the operation of internal components. In addition to possible user discomfort, electrostatic discharges may damage sensors and electronics. Electrostatic charges are dissipated from the AMD using an electrostatic dissipation structure and conductive wheels. A conductive path between a chassis ground, the electrostatic dissipation structure, and the conductive wheels improves the dissipation of electrostatic charges. Electrostatic charges are also dissipated from components by mounting the components using conductive materials. Sensors may be affixed to a support structure that is affected by thermal expansion. Thermal expansion may distort precise positioning of sensors, reducing accuracy of sensor data. An elastomeric foam may be used to mount sensors to a support structure, allowing for thermal expansion without distorting the positioning of the sensors.

Electrostatic dissipation system for an autonomous mobile device

Growing community of inventors

Belmont, CA, United States of America

Eric Foxlin