Massachusetts Institute of Technology

Toyota Research Institute, Inc.

Harvard College

The Boeing Company

The General Hospital Corporation

Ava Robotics Inc.

Children's Medical Center Corporation

Eth Zurich

Daniela Rus

Sertac Karaman

Guy Rosman

Igor Gilitschenski

Alyssa Pierson

Jeffrey Ian Lipton

Alexander Amini

Robert J Wood

Wilko Schwarting

Branko Sarh

Dina Katabi

Andrew Dominic Marchese

Youssef Saleh

Swarun Suresh Kumar

Marcio Macedo

Michael T Tolley

Aidan Fay

Dana Damian

Shuguang Li

Lillian Chin

Kyle W Gilpin

Saman Amarasinghe

Shuhei Miyashita

Stephanie Gil

Cagdas Denizel Onal

Changhyun Choi

Felix Maximilian Naser

Robert Bruce MacCurdy

Alexander J Wallar

Dan Feldman

John W Romanishin

Javier Alonso-Mora

George M Whitesides

Wojciech Matusik

William T Freeman

Hari Balakrishnan

Stephen G McGill

Luke S Fletcher

Xin Chen

David Kenneth Gifford

John J Leonard

Gregory W Wornell

Fredo Durand

Roland Siegwart

Thomas Bortfeld

Moses Theodore Ort

Antonio Torralba

Andrew Kiminari Sugaya

John William Fisher, Iii

Daniel M Vogt

Erik D Demaine

Carrick Detweiler

Eduardo R Torres-Jara

Susu Yan

Minoru Brandon Araki

Cynthia Rueyi Sung

Nicholas W Bartlett

Josephine Anna Eleanor Hughes

Mark Chounlakone

Andrew Spielberg

Gloria Chang

Andrei Cramariuc

Cristian-Ioan Vasile

Brandon Araki

Xiao Li

Thomas Buchner

Sejoon Lim

Jay Flanz

Anshula Gandhi

Cesar Cadena

Javier Alonso Mora

Samuel R Madden

Daniel A Hashimoto

Julia Moseyko

Ozanan R Meireles

Thomas Ward

Jacob Phillips

Samuel M Felton

Joseph J DelPreto

Yutong Ban

Ankur M Mehta

Marek W Doniec

Iuliu Vasilescu

Christina Liao

Alexander Bahr

Arjun Gupta

Samitha Samaranayake

A controller for an autonomous vehicle is trained using simulated paths on a roadway and simulated observations that are formed by transforming images previously acquired on similar paths on that roadway. Essentially an unlimited number of paths may be simulated, enabling optimization approaches including reinforcement learning to be applied to optimize the controller.

Simulation-based training of an autonomous vehicle

Systems and methods are provided for generating a statistical parameter representing a state of a surgical procedure from sensor data. Sensor data representing a time period. is received from a sensor. Numerical features representing the time period are generated from the sensor data. Each of a plurality of long short term memory units are updated according to the plurality of numerical features via a message passing process. The long short term memory units are connected to form a graph, with a first set of the long short term memory units representing a plurality of nodes of the graph and a second set of the long short term memory units representing a plurality of hyperedges of the graph. A statistical parameter representing a state of the surgical procedure for the time period is derived from an output of one of the long short term memory units and provided to a user.

Interpretation of intraoperative sensor data using concept graph neural networks

A system and method for patient positioning during radiotherapy. The system can include a patient support structure configured to receive a patient during a radiotherapy process using a radiotherapy source to deliver a therapy to the patient when positioned on the patient support structure, a patient positioning system configured to adjust a position of the patient support structure relative to the radiotherapy source, a flexible actuator configured to secure the patient to the patient support and adjust a position of the patient relative to the patient support, and an imaging system configured to acquire imaging data of the patient, the patient support, and the flexible actuator during the radiotherapy process.

Systems and methods for patient positioning during radiotherapy

An autonomous, mobile robotic device (AMR) is configured with one or more UVC radiation sources, and operates to traverse a path while disinfecting an interior space. Each UVC radiation source is connected to the AMR by an articulating arm that is controlled to orient each source towards a feature or surface that is selected for disinfection during the time that the AMR is moving through the space. The location of each feature selected for disinfection can be mapped, and this map information, a current AMR location and pose can be used to generate signals that are used to control the articulating arm to orient each UVC lamp towards a feature that is selected for disinfection.

Autonomous, mobile robotic apparatus for applying disinfection to an interior area

A method of generating an output trajectory of an ego vehicle is described. The method includes extracting high-level features from a bird-view image of a traffic environment of the ego vehicle. The method also includes generating, using an automaton generative network, an automaton including an automaton state distribution describing a behavior of the ego vehicle in the traffic environment according to the high-level features. The method further includes generating the output trajectory of the ego vehicle according to extracted bird-view features of the bird-view image and the automaton state distribution describing the behavior of the ego vehicle in the traffic environment.

Method for learning an explainable trajectory generator using an automaton generative network

Method and apparatus for planning a disinfection path for an autonomous, mobile robotic device

In some aspects, a system comprises a computer hardware processor and a non-transitory computer-readable storage medium storing processor-executable instructions for receiving, from one or more sensors, sensor data relating to a robot; generating, using a statistical model, based on the sensor data, first control information for the robot to accomplish a task; transmitting, to the robot, the first control information for execution of the task; and receiving, from the robot, a result of execution of the task.

Systems and methods for distributed training and management of AI-powered robots using teleoperation via virtual spaces

Understanding the intent of human drivers and adapting to their driving styles is used to increased efficiency and safety of autonomous vehicles (AVs) by enabling them to behave in safe and predictable ways without requiring explicit inter-vehicle communication. A Social Value Orientation (SVO), which quantifies the degree of an agent's selfishness or altruism, is estimated by the AV for other vehicles to better predict how they will interact and cooperate with others. Interactions between agents are modeled as a best response game wherein each agent negotiates to maximize their own utility. A dynamic game solution uses the Nash equilibrium, yielding an online method of predicting multi-agent interactions given their SVOs. This approach allows autonomous vehicles to observe human drivers, estimate their SVOs, and generate an autonomous control policy in real time.

Social behavior for autonomous vehicles

An approach to autonomous navigation of a vehicle augments a static map of an environment with a clutter map characterizing a risk of encountering an object that is not represented in the static map of the environment. For example, the clutter map may be based on locations and velocities of those objects, and route planning may avoid planning a path through locations that have a high risk of occupancy, and therefore potential delay or collision.

Autonomous navigation in a cluttered environment

Systems and methods described herein relate to estimating risk associated with a vehicular maneuver. One embodiment acquires a geometric representation of an intersection including a lane in which a vehicle is traveling and at least one other lane; discretizes the at least one other lane into a plurality of segments; determines a trajectory along which the vehicle will travel; estimates a probability density function for whether a road agent external to the vehicle is present in the respective segments; estimates a traffic-conflict probability of a traffic conflict in the respective segments conditioned on whether an external road agent is present; estimates a risk associated with the vehicle following the trajectory by integrating a product of the probability density function and the traffic-conflict probability over the at least one other lane and the plurality of segments; and controls operation of the vehicle based, at least in part, on the estimated risk.

Systems and methods for estimating the risk associated with a vehicular maneuver

An artificial muscle system includes a collapsible skeleton, a flexible skin, and a muscle actuation mechanism. The collapsible skeleton is contained inside a volume defined, at least in part, by the flexible skin. The flexible skin and the collapsible skeleton are configured for the flexible skin to provide a pulling force on the collapsible skeleton when a pressure difference exists between the inside of the sealed volume and a surrounding environment to change at least one of the dimensions and thus geometry of the collapsible skeleton. The muscle actuation mechanism includes at least one of the following to deploy or contract the collapsible skeleton: (a) a fluid displacing, releasing, or capturing mechanism configured to increase or decrease fluid pressure inside the sealed volume; and (b) a heating or cooling element configured to change the temperature of fluid in the sealed volume.

Programmable multi-scale fluidic artificial muscles and pistons

A wearable article comprising a knitted fabric formed in the shape of a glove. A force sensing element coupled to the fabric, the force sensing element comprising a resistive sensing system and a fluidic sensing system comprising one or more soft tubes coupled to a surface of the wearable glove wherein the resistive and fluid sensing systems correspond to first and second different sensor modalities which are physically decoupled. Control circuitry is coupled to receive signals from both the resistive sensing system and the fluidic sensing system and to combine resistive and fluidic sensing system signals provided thereto to perform at least one of: pose estimation, environment sensing, human state sensing, and static and dynamic task identification.

Wearable glove with hybrid resistive-pressure sensors

Described is a method and system for vehicle routing and request assignment which incorporates a prediction of future demand. The method seamlessly integrates sampled future requests into request assignments and vehicle routing.

On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment with future requests

Described are concepts, systems, devices and techniques for real-time high-capacity ride-sharing that (i) scales to large numbers of passengers and trips and (ii) dynamically generates routes (e.g. optimal or near optimal routes) in response to online demand and vehicle locations.

System for on-demand high-capacity ride-sharing via dynamic trip-vehicle assignment and related techniques

Methods and apparatus for a vibration dampening system having an adaptor with a user contact surface and a power tool contact surface. The adaptor can include a core to reduce vibration transfer from the tool to the hands of a user. In embodiments, the core comprises a viscoelastic material that lightens a base elastomer to form liquid-filled closed cells structures.

Vibration absorber for power tools

Growing community of inventors

Weston, MA, United States of America

Daniela Rus