Toyota Research Institute, Inc.

Toyota Jidosha Kabushiki Kaisha

Ryan Marcotte

Marcus Hammond

Daniele Molinari

Constantin Franziskus Dominik Hubmann

Harsh Virendra Pandya

A system for producing a trajectory from a diverse set of possible movements can include a processor and a memory. The memory can store a possible movement production module and a trajectory production module. The possible movement production module can include instructions that cause the processor to: (1) produce a set of possible movements of a mobile robot with respect to a challenge, (2) determine a measure of diversity between a first possible movement and a second possible movement, and (3) produce a subset. Measures of diversity associated with possible movements included in the subset can be larger than measures of diversity associated with possible movements excluded from the subset. The trajectory production module can include instructions that cause the processor to: (1) produce trajectories associated with the possible movements included in the subset and (2) cause the mobile robot to move according to one of the trajectories.

Producing a trajectory from a diverse set of possible movements

A method of controlling availability of autonomy functions of a vehicle includes determining one or more uncertainty levels, each corresponding to a driving data stream including driving data, wherein the uncertainty levels correspond to a probability of a collision or driving off the roadway. The method further includes generating a total uncertainty level based on the one or more uncertainty levels and disabling a first autonomy function based on availability criteria of the first autonomy function. The availability criteria define a first threshold of the total uncertainty level. The method further includes providing a second autonomy function based on the second autonomy function's availability criteria that include a total uncertainty threshold higher than the first threshold.

Layered architecture for availability of advanced driver assistance features

A method for identifying high-risk driving situations in driving data may include receiving driving data, identifying trigger events in the driving data, and using the trigger events in combination with first portions of the driving data corresponding to periods of time preceding the trigger events, training a machine learning model to identify features, in the driving data, associated with the trigger events. The method may further include using second portions of the driving data where no trigger events are identified, further training the machine learning model to ignore features common to both the first portions and the second portions. The method further includes detecting a high risk driving situation in real time driving data by using the machine learning model to identify the features associated with the trigger events, and performing a defensive driving maneuver in response to the detection of the high risk driving situation.

Systems and methods for identifying high-risk driving situations from driving data

A system and related method determines implicit lane boundaries by generating a bird's eye view of a portion of a road having a first lane and a second lane from environment data having information related to the road, overlaying a grid having cells onto the bird's eye view of the portion of the road, determining cells of the grid that form at least portions of the first lane of the road, determining cells of the grid that form at least portions of the second lane of the road, and determining a probability for one or more cells of the grid indicating a likelihood that a vehicle will travel upon portions of the road represented by the cells of the grid when traveling from the first lane to the second lane. The probability for one or more cells of the grid may be generated by a neural network trained with training data.

Growing community of inventors

Ann Arbor, MI, United States of America

Ryan Marcotte