Honda Motor Co., Ltd.

University of California

Other

Xerox Corporation

Western Digital Technologies, Inc.

Masayoshi Tomizuka

Takashi Ishida

Sudhendu Rai

Guoxiao Guo

Kikuo Fujimura

Wei Xi

Martin Krucinski

David Francis Isele

Paul Sagues

David R Kamprath

Alireza Nakhaei Sarvedani

Shuichi Kamiyama

Xu Qi Chen

David M Auslander

Ruzena Bajcsy

Ran Tian

Perry Y Li

Roberto Horowitz

Liting Sun

Minghui Zheng

Eric John Mica

Waiman Meinhold

Joel Alfredo Loeza

Yeping Hu

Carlo Cloet

Robert Peter Matthew

Systems and methods for incorporating latent states into robotic planning are provided. In one embodiment, the method includes identifying an agent team including at least one robotic agent and at least one human agent. The method also includes receiving sensor data associated with relative physical parameters between the at least one robotic agent and the at least one human agent. The method further includes modeling the latent states of the at least one human agent as a behavior model. The latent states describe cognition of the at least one human agent. The method includes calculating a first belief state based on the relative physical parameters and the behavior model. The method yet further includes predicting future probabilities of future observations at a second the future probabilities.

Systems and methods for incorporating latent states into robotic planning

Interaction-aware decision making may include training a first agent based on a first policy gradient, training a first critic based on a first loss function to learn goals in a single-agent environment using a Markov decision process, training a number N of agents based on the first policy gradient, training a second policy gradient and a second critic based on the first loss function and a second loss function to learn goals in a multi-agent environment using a Markov game to instantiate a second agent neural network, and generating an interaction-aware decision making network policy based on the first agent neural network and the second agent neural network. The N number of agents may be associated with a driver type indicative of a level of cooperation. When a collision occurs, a negative reward or penalty may be assigned to each agent involved based on a lane priority level of respective agents.

Interaction-aware decision making

Semi-passive control system () comprises a pneumatic spring actuator (), a pressure regulator () in communication with the pneumatic spring actuator (), a hydraulic locking actuator (), a hydraulic valve () in communication with actuator (), a power source (), a pulley wheel (), and a cable () having a first end in contact with pulley wheel (), first and second side portions () extending from opposing sides of pulley wheel (), and a second end adapted to connect to an orthosis device (). At least one cable clamp () attaches to second side portion () of cable () and interconnects cable () to shafts () of actuators (). A central control unit () includes a processor () and a computer readable storage medium () having program instructions stored thereon for execution by the central control unit to adjust stiffness, damping or stiffness and damping parameters.

Semi-passive control system and method for assistive orthoses

A data storage device includes a disk, a head, a microactuator, a coarse actuator, and a servo controller. The microactuator is configured to position the head relative to the disk. The coarse actuator is configured to position the microactuator relative to the disk. The servo controller is configured to generate an adjusted position error signal based on a position error signal and an estimated microactuator position signal. The servo controller is also configured to filter the adjusted position error signal with a shaping filter to generate a filtered position error signal, and to provide sliding mode control of the coarse actuator based at least partially on the filtered position error signal.

Data storage devices and methods with frequency-shaped sliding mode control

A method of synchronizing the arrival of copy sheets at a photoreceptor in an image processing having a copy sheet path having a plurality of segments coupled at given transfer zones, a plurality of copy sheet drives, an image transfer station, a photoreceptor and a controller. The controller directs the image processing apparatus by tracking the movement of copy sheets at the image transfer station in relation to the movement of the photoreceptor, monitoring the movement of copy sheets at the transfer zones, determining the need to adjust the spacing of copy sheets along the plurality of segments of the copy sheet path, and suitably activating selected copy sheet drives.

Interpaper spacing control in a media handling system

A method and apparatus for starting a cold internal combustion engine under optimum conditions. Engine r.p.m. is maintained to a desired value until either the car is started, driven, or the temperature of the engine reaches a predetermined value, whichever first occurs. During this time, the ratio between the air and fuel fed to the engine is kept at the optimum values corresponding to the prevailing engine conditions during this time.

Engine cold starting

Growing community of inventors

Berkeley, CA, United States of America

Masayoshi Tomizuka