Massachusetts Institute of Technology

Toyota Research Institute, Inc.

Magna Electronics Inc.

Eth Zurich

Sertac Karaman

Daniela Rus

Igor Gilitschenski

Guy Rosman

Alyssa Pierson

Alexander Amini

Wilko Schwarting

Felix Maximilian Naser

William T Freeman

Stephen G McGill

Luke S Fletcher

John J Leonard

Gregory W Wornell

Fredo Durand

Antonio Torralba

Ramiro Almeida

Moses Theodore Ort

Minoru Brandon Araki

Ruijie He

Javier Alonso Mora

Julia Moseyko

Cristian-Ioan Vasile

Xiao Li

Jacob Phillips

Brandon Araki

Anshula Gandhi

Jenny Larios-Berlin

Ryan C C Chin

Albert Huang

Arjun Gupta

Christina Liao

Cesar Cadena

Andrei Cramariuc

Jonathan Marston

Daniela L Rus

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

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

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

A method, computer program product, and computing system for operating an autonomous vehicle; monitoring the operation of a plurality of computing devices within the autonomous vehicle; and in response to detecting the failure of one or more of the plurality of computing devices, switching the autonomous vehicle from a nominal autonomous operational mode to a degraded autonomous operational mode.

Redundancy system and method

The present disclosure provides systems and methods to detect occluded objects using shadow information to anticipate moving obstacles that are occluded behind a corner or other obstacle. The system may perform a dynamic threshold analysis on enhanced images allowing the detection of even weakly visible shadows. The system may classify an image sequence as either 'dynamic' or 'static', enabling an autonomous vehicle, or other moving platform, to react and respond to a moving, yet occluded object by slowing down or stopping.

Systems and methods of detecting moving obstacles

Systems and methods for predicting the trajectory of an object are disclosed herein. One embodiment receives sensor data that includes a location of the object in an environment of the object; accesses a location-specific latent map, the location-specific latent map having been learned together with a neural-network-based trajectory predictor during a training phase, wherein the neural-network-based trajectory predictor is deployed in a robot; inputs, to the neural-network-based trajectory predictor, the location of the object and the location-specific latent map, the location-specific latent map providing, to the neural-network-based trajectory predictor, a set of location-specific biases regarding the environment of the object; and outputs, from the neural-network-based trajectory predictor, a predicted trajectory of the object.

Systems and methods for predicting the trajectory of an object with the aid of a location-specific latent map

A method is disclosed for use in a planning agent, the method including: identifying a first agent in a vicinity of the planning agent; identifying a location of the first agent and a velocity of the first agent; calculating a set of occupancy costs for the first agent, each occupancy cost in the set of occupancy costs being associated with a different respective location in the vicinity of the planning agent, each occupancy cost in the set of occupancy costs being calculated at least in part based on a cost function that depends on the location of the first agent and the velocity of the first agent; and changing at least one of speed or direction of travel of the planning agent based on the set of occupancy costs.

Navigating congested environments with risk level sets

An approach to place recognition from an image makes use of the detection of objects at a set of known places as well as at an unknown place. Images of the detected objects in an image of the unknown place are processed to yield respective numerical descriptors, and these descriptors are used to compare the unknown place to the known places to recognize the unknown place. At least some embodiments make use of a trained parameterized image processor to transform an image of an object to an object descriptor, and the training of the processor is meant to preserve distinctions between different instances of a type of object, as well as distinctions between entirely different types of objects.

Visual object instance descriptor for place recognition

Systems and methods described herein relate to vehicular navigation and localization. One embodiment extracts perceptual features from sensor data; extracts unrouted-map features from unrouted map data; combines the perceptual features and the unrouted-map features to produce first combined features data; outputs, based at least in part on the first combined features data, parameters of a probability distribution for one or more steering trajectories that are available to a vehicle; and performs a localization of the vehicle based, at least in part, on the parameters of the probability distribution.

Systems and methods for vehicular navigation and localization

A method of non-line-of-sight (NLoS) obstacle detection for an ego vehicle is described. The method includes capturing a sequence of images over a period with an image capture device. The method also includes storing the sequence of images in a cyclic buffer. The method further includes registering each image in the cyclic buffer to a projected image. The method includes performing the registering by estimating a homography H for each frame of the sequence of images to project to a view point of a first frame in the sequence of images and remove motion of the ego vehicle in the projected image. The method also includes enhancing the projected image. The method further includes classifying the projected image based on a scene determination. The method also includes issuing a control signal to the vehicle upon classifying the projected image.

Infrastructure-free NLoS obstacle detection for autonomous cars

Growing community of inventors

Cambridge, MA, United States of America

Sertac Karaman