Lorenzo Caminiti - Ann Arbor MI, US Michael E. Samples - Toledo OH, US Michael R. James - Dearborn MI, US Kenneth P. Laberteaux - Ann Arbor MI, US Derek S. Caveney - Ann Arbor MI, US Jeff B. Rogers - Ann Arbor MI, US
Assignee:
Toyota Motor Engineering & Manufacturing North America, Inc. - Erlanger KY
International Classification:
G01M 17/00 G06F 7/00 G06F 19/00
US Classification:
701 29, 701 33, 340 31, 340 343, 340 36
Abstract:
A computing platform for multiple intelligent transportation systems in an automotive vehicle having a plurality of sensors which generate output signals representative of various vehicle operating parameters. The platform includes a vehicle data center which receives input signals from the vehicle sensors and the vehicle data center is configured to transform these input signals into output signals having a predetermined format for each of the vehicle operating parameters. A central processing unit receives the output signal from the vehicle data and is programmed to process the vehicle data center output signals for each of the intelligent transportation systems and generate the appropriate output signals as a result of such processing.
Combining Driver And Environment Sensing For Vehicular Safety Systems
An apparatus for assisting safe operation of a vehicle includes an environment sensor system detecting hazards within the vehicle environment, a driver monitor providing driver awareness data (such as a gaze track), and an attention-evaluation module identifying hazards as sufficiently or insufficiently sensed by the driver by comparing the hazard data and the gaze track. An alert signal relating to the unperceived hazards can be provided.
Michael Edward Samples - Ann Arbor MI, US Michael Robert James - Northville MI, US
Assignee:
Toyota Motor Engineering & Manufacturing North America, Inc. - Erlanger KY
International Classification:
G05D 1/00
US Classification:
701 1, 701 25, 701 23
Abstract:
Method, storage medium and system of optimizing a destination for a vehicle by obtaining a map corresponding to a desired destination of the vehicle and identifying objectives of the map based on multiple parameters including collision avoidance, driver time, legal constraints and social consensus. A cost function is constructed to determine an optimal destination based on a proximity to the desired destination and the identified objectives, and an optimal destination is identified by minimizing a value of the cost function.
Real-Time 3D Point Cloud Obstacle Discriminator Apparatus And Associated Methodology For Training A Classifier Via Bootstrapping
Michael Edward Samples - Ann Arbor MI, US Michael Robert James - Northville MI, US
Assignee:
Toyota Motor Engineering & Manufacturing North America, Inc. - Erlanger KY
International Classification:
G06K 9/62 G06K 9/00
US Classification:
382159, 382104
Abstract:
Training a strong classifier by classifying point cloud data with a first classifier, inferring a first terrain map from the classified point cloud data, reclassifying the point cloud data with the first classifier based on the first terrain map, and training a second classifier based on the point cloud data reclassified with the first classifier based on the terrain map. The point cloud data is then classified with the second classifier, and the procedure followed with the first classifier is iteratively repeated until a strong classifier is determined. A strong classifier is determined when a probability of a terrain map matching a given terrain for the strong classifier is approximately equal to a probability of a terrain map matching the given terrain for a prior trained classifier.
Relevancy Check For Vehicle Safety Messages Using A Path History
Lorenzo Caminiti - Ann Arbor MI, US Derek S. Caveney - Ann Arbor MI, US Kenneth P. Laberteaux - Ann Arbor MI, US Michael E. Samples - Toledo OH, US
Assignee:
Toyota Engineering & Manufacturing North America, Inc. - Erlanger KY
International Classification:
G08G 1/16
US Classification:
701301, 701300
Abstract:
There is disclosed a method for avoiding a collision in a vehicle including the steps of: providing a transmitting vehicle, providing a receiving vehicle, creating data information in the transmitting vehicle, sending the data information to the receiving vehicle, and determining the relevancy of the data information to the receiving vehicle using a current position and heading of the receiving vehicle.
Michael Robert James - Northville MI, US Michael Edward Samples - Ann Arbor MI, US
Assignee:
Toyota Motor Engineering & Manufacturing North America, Inc. - Erlanger KY
International Classification:
G06N 5/04
US Classification:
706 52
Abstract:
An object tracking system and method operable to minimize processing time for tracking objects is provided. The system includes a pair of filters operable to make associations between dynamic objects newly detected and previously detected. One of the pair of filters makes an association when the predicted location of the previously detected objects is within a predetermined distance of the newly detected object. The other of the pair of filters makes an association based upon the probability that a newly detected dynamic object is a previously detected dynamic object. The remaining unassociated dynamic objects are then localized so as to form discrete matrices for optimization filters.
Tracking On-Road Vehicles With Sensors Of Different Modalities
Avdhut S. JOSHI - Ann Arbor MI, US Michael R. James - Northville MI, US Michael E. Samples - Ann Arbor MI, US
Assignee:
TOYOTA MOTOR ENG. & MFTG. NORTH AMERICA - Erlanger KY
International Classification:
G06F 17/00
US Classification:
701 1, 702150
Abstract:
A vehicle system includes a first sensor and a second sensor, each having, respectively, different first and second modalities. A controller includes a processor configured to: receive a first sensor input from the first sensor and a second sensor input from the second sensor; detect, synchronously, first and second observations from, respectively, the first and second sensor inputs; project the detected first and second observations onto a graph network; associate the first and second observations with a target on the graph network, the target having a trajectory on the graph network; select either the first or the second observation as a best observation based on characteristics of the first and second sensors; and estimate a current position of the target by performing a prediction based on the best observation and a current timestamp.
Calibrating Sensor Alignment With Applied Bending Moment
- Redmond WA, US Navid POULAD - San Jose CA, US Dapeng LIU - Redmond WA, US Trevor Grant BOSWELL - Madera CA, US Roy Joseph RICCOMINI - Saratoga CA, US Michael Edward SAMPLES - Redmond WA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
H04N 13/246 H04N 13/366 G06F 3/01 H04N 13/239
Abstract:
Examples are disclosed that relate to calibration data related to a determined alignment of sensors on a wearable display device. One example provides a wearable display device comprising a frame, a first sensor and a second sensor, one or more displays, a logic system, and a storage system. The storage system comprises calibration data related to a determined alignment of the sensors with the frame in a bent configuration and instructions executable by the logic system. The instructions are executable to obtain a first sensor data and a second sensor data respectfully from the first and second sensors, determine a distance from the wearable display device to a feature based at least upon the first and second sensor data using the calibration data, obtain a stereo image to display based upon the distance from the wearable display device to the feature, and output the stereo image via the displays.
Toyota Technical Center - Ann Arbor, MI since May 2005
AI & Robotics Senior Engineer
Altarum May 2003 - Aug 2004
AI Research Intern
University of Michigan May 2002 - Sep 2002
Undergraduate Research
Education:
University of Michigan 2001 - 2006
B.S., Computer Science & Mathematics
Skills:
C++ Machine Learning Computer Vision Artificial Intelligence Algorithms Data Mining Python Robotics Simulations Computer Science Camera Calibration Slam Probabilistic Models R&D Navigation Optimization Numerical Methods Sensors Autonomous Vehicles Mountain Biking Path Planning R Distributed Systems Mapping Augmented Reality Virtual Reality
Interests:
Kayaking Investing Rock Climbing Snowboarding Soccer Running Coding