Amazon Technologies, Inc.

Sheng Chen

Hakan Boyraz

Xiaohan Nie

Baoyuan Liu

Christopher David Brown

Marshall Friend Tappen

Aleksandar Kojic

Hamed Pirsiavash

Michael Lawrence LeKander

Hitesh Arora

Ayan Tuhinendu Sinha

Mark Buckler

Todd Hester

The present disclosure generally relates to a system of a delivery device for combining sensor data from various types of sensors to generate a map that enables the delivery device to navigate from a first location to a second location to deliver an item to the second location. The system obtains data from RGB, LIDAR, and depth sensors and combines this sensor data according to various algorithms to detect objects in an environment of the delivery device, generate point cloud and pose information associated with the detected objects, and generates object boundary data for the detected objects. The system further identifies object states for the detected object and generates the map for the environment based on the detected object, the generated object proposal data, the labeled point cloud data, and the object states. The generated map may be provided to other systems to navigate the delivery device.

Systems and methods of obstacle detection for automated delivery apparatus

Techniques are generally described for fusing sensor data of different modalities using a transformer. In various examples, first sensor data may be received from a first sensor and second sensor data may be received from a second sensor. A first feature representation of the first sensor data may be generated using a first machine learning model and a second feature representation of the second sensor data may be generated using a second machine learning model. In some examples, a modified first feature representation of the first sensor data may be generated based at least in part on a self-attention mechanism of a transformer encoder. The modified first feature representation may be generated based at least in part on the first feature representation and the second feature representation. A computer vision task may be performed using the modified first feature representation.

Sensor data fusion using cross-modal transformer

Autonomous ground vehicles capture images during operation, and process the images to recognize ground surfaces or features within their vicinity, such as by providing the images to a segmentation network trained to recognize the ground surfaces or features. Semantic maps of the ground surfaces or features are generated from the processed images. A point on a semantic map is selected, and the autonomous ground vehicle is instructed to travel to a location corresponding to the selected point. The point is selected in accordance with one or more goals, such as to maintain the autonomous ground vehicle at a selected distance from a roadway or other hazardous surface, or along a centerline of a sidewalk.

Semantic navigation of autonomous ground vehicles

An autonomous delivery robot system to enable delivery of a product to a customer is described. One autonomous ground vehicle (AGV) includes a processing device that receives a delivery request comprising a route divided into multiple navigation segments and computes a navigable space from perception data stored in a perception map. The perception map is a robot-centered local map that stores the perception data indicative of the surroundings of the AGV. The processing device computes a cost inflation from the perception data stored in the perception map, determines a sub-goal that is on the navigable space and reachable by the AGV using the navigable space and the cost inflation, and determines a path to achieve the sub-goal using the using the navigable space and the cost inflation. The processing device controls one or more actuators to move along the path.

Navigation directly from perception data without pre-mapping

Growing community of inventors

Seattle, WA, United States of America

Sheng Chen