Abstract: Methods and systems for navigating a mobile robot through a crowded pedestrian environment by selecting and following a particular pedestrian are described herein. In one aspect, a navigation model directs a mobile robot to follow a pedestrian based on the position and velocity of nearby pedestrians and the current and desired positions of the mobile robot in the service environment. The mobile robot advances toward its desired destination by following the selected pedestrian. By repeatedly sampling the positions and velocities of nearby pedestrians and the current location, the navigation model directs the mobile robot toward the endpoint location. In some examples, the mobile robot selects and follows a sequence of different pedestrians to navigate to the desired endpoint location. In a further aspect, the navigation model determines whether following a particular pedestrian will lead to a collision with another pedestrian. If so, the navigation model selects another pedestrian to follow.

Abstract: A service robot includes a wheeled, robotic vehicle and a movable payload platform. A position of the payload platform is controlled to reduce the distance between the center of mass of the service robot and a center of rotation of the vehicle moving along a motion trajectory. Induced centrifugal forces are reduced, allowing for safe operation at higher speeds. In some examples, the payload platform is moved such that the center of mass of the service robot is approximately aligned with the center of rotation of the vehicle. In some embodiments, at least one wheel of the service robot is controlled to maintain a level orientation of the service robot as it traverses uneven terrain. In some embodiments, the service robot includes an inflatable torso structure that allows an upper body robot to bend in a controlled manner to interact with users and a payload loaded onto the payload platform.

Abstract: Methods and systems for assisting hemiplegic and hemiparetic patients are described herein. A wearable gripper system assists a user with one functional hand to independently perform basic tasks. A wearable gripper is located on the forearm above a disabled hand. The user controls the wearable gripper easily and intuitively based on gestures measured by an instrumented wristband device. Movements detected at the functioning wrist and forearm are translated into the motion control commands communicated to the actuators of the wearable gripper. In this manner, the wearable gripper assists the user to manipulate objects in lieu of the disabled hand. In some embodiments, a number of conductive, stretchable string sensors are wrapped around the hand of a user to estimate wrist and hand motion. In some embodiments, a gripper actuator includes two or more fingers, each having a location dependent shape profile and compliance to accommodate different manipulation tasks.

Abstract: Methods and systems for navigating a mobile robot through a crowded pedestrian environment based on a trained navigation model are described herein. The trained navigation model receives measurement data identifying nearby pedestrians and the velocity of each nearby pedestrian relative to the mobile robot, and the current position and desired endpoint position of the mobile robot in the crowded pedestrian environment. Based on this information, the trained navigation model generates command signals that cause the mobile robot to adjust its velocity. By repeatedly sampling the velocities of surrounding pedestrians and current location, the navigation model directs the mobile robot toward the endpoint location with a minimum of disruption to the pedestrian traffic flows. The navigation model is trained to emulate desirable pedestrian walking behaviors in a crowded pedestrian environment by tracking the movement of a behavioral trainer through a crowded pedestrian environment.

Abstract: Methods and systems for autonomously interacting with persons in a public environment to store and transport their personal material items are described herein. A service robot includes one or more secure storage cells, and is configured to collect items such as personal belongings, refuse, etc., from users and transport the collected items to different locations. The service robot maneuvers through a crowded environment autonomously, avoiding collisions with people and objects, and minimizing disturbances to traffic flow. Users indicate a desire to store and transport items to a desired location. In response, the service robot unlocks a lid of a storage cell, and the user is able to load material items. In some examples, access to the storage cell is controlled based on access codes. In some examples, access to the storage cell is controlled based on receipt of an electronic payment.

Abstract: Methods and systems for passively supporting the upper body of a human user working at or near the ground are described herein. In one aspect, an upper body support system braces the torso of a human user against a surface of the work environment. This frees the hands and arms of the human user that would otherwise be occupied supporting the human torso. This enables a human user to comfortably use both hands to execute a particular work task. The upper body support system performs the support functionality described herein without the use of active devices. The upper body support system includes one or more passive upper body support assemblies each coupled to a harness assembly worn by the human user. Each passive upper body support assembly includes an extensible body support limb that extends toward the surface of the working environment and supports the human user compliantly.

Abstract: Methods and systems for providing a reliable hands-free interface between a user and a computing device are presented herein. The interface system includes a gaze tracking system, display system, and head motion tracking system all attached to a frame that is mountable to the head of a user. Eye movements are tracked to determine when the gaze of a user has settled on a particular image displayed by the display system. After a fixed gaze has been identified, it is determined whether the user is moving his/her head in a confirmatory head gesture. The user selection is verified by determining whether the gaze of the user remains fixed to the selected image while executing the confirmatory gesture. This ensures that the gaze of the user remains focused on the selected image projected by the display, rather than an object in the surrounding environment.