Carl K. Wellington - Pittsburgh PA, US Aaron C. Courville - Montreal, CA Anthony J. Stentz - Pittsburgh PA, US
Assignee:
Carnegie Mellon University - Pittsburgh PA
International Classification:
G06K 9/00
US Classification:
382154, 382156, 382157, 382159
Abstract:
The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.
System And Method For Generating A Terrain Model For Autonomous Navigation In Vegetation
The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.
Method And System For Estimating Navigability Of Terrain
Anthony Stentz - Pittsburgh PA, US Carl Knox Wellington - Pittsburgh PA, US
Assignee:
Carnegie Mellon University - Pittsburgh PA
International Classification:
G01C 21/26 G01C 21/28 G01C 21/00
US Classification:
701 26, 701 28, 701223
Abstract:
A method and system for detecting an obstacle comprises a terrain estimator for estimating a local terrain surface map based on at least one of range data points, color data, and infrared data gathered by electromagnetic perception focused in front of a vehicle. The map is composed of a series of terrain cells. An analyzer estimates at least one of predicted roll data, predicted pitch data, predicted ground clearance data, and predicted friction coefficient data based on the estimated terrain map for respective terrain cells and vehicular constrain data. A local planner determines predicted vehicle control data for terrain cells within the terrain along a planned path of the vehicle. One or more vehicle sensors sense at least one of actual roll data, actual pitch data, actual ground clearance data, and actual friction coefficient data for the terrain cells when the vehicle is coextensively positioned with the corresponding terrain cell. A learning module adjusts at least one of the terrain map estimation and the control data determination based on the sensed actual data.
Systems And Methods For Object Detection And Motion Prediction By Fusing Multiple Sensor Sweeps Into A Range View Representation
- San Francisco CA, US Gregory P. Meyer - Pittsburgh PA, US Jake Scott Charland - Winter Park CO, US Shivam Gautam - Pittsburgh PA, US Shreyash Pandey - Pittsburgh PA, US Carl Knox Wellington - Pittsburgh PA, US
Systems and methods for detecting objects and predicting their motion are provided. In particular, a computing system can obtain a plurality of sensor sweeps. The computing system can determine movement data associated with movement of the autonomous vehicle. For each sensor sweep, the computing system can generate an image associated with the sensor sweep. The computing system can extract, using the respective image as input to one or more machine-learned models, feature data from the respective image. The computing system can transform the feature data into a coordinate frame associated with a next time step. The computing system can generate a fused image. The computing system can generate a final fused image. The computing system can predict, based, at least in part, on the final fused representation of the plurality of sensors sweeps from the plurality of sensor sweeps, movement associated with the feature data at one or more time steps in the future.
Systems And Methods For Low-Latency Braking Action For An Autonomous Vehicle
- San Francisco CA, US Michael W. Bode - Pittsburgh PA, US Randy Warner - Allison Park PA, US Dillon Collins - Pittsburgh PA, US Anurag Kumar - Pittsburgh PA, US Carl Knox Wellington - Pittsburgh PA, US
International Classification:
B60T 7/22 B60T 8/172 G08G 1/16
Abstract:
Systems and methods for implementing a low-latency braking action for an autonomous vehicle are provided. A computing system can include a vehicle autonomy system comprising one or more processors configured to determine a motion plan for an autonomous vehicle based at least in part on sensor data from one or more sensors of the autonomous vehicle. The computing system can further include a low-latency braking system comprising one or more processors configured to determine that the autonomous vehicle has a likelihood of colliding with an object in a surrounding environment based at least in part on a previously-determined motion plan obtained from the vehicle autonomy system. In response to determining that the autonomous vehicle has a likelihood of colliding with the object in the surrounding environment, the low-latency braking system can further be configured to implement a braking action for the autonomous vehicle.
The present disclosure provides systems and methods for detecting, localizing, and classifying objects that are proximate to an autonomous vehicle. A sensor system can include one or more ranging systems and a plurality of cameras. The plurality of cameras can be positioned such that a field of view for each camera of the plurality of cameras overlaps a field of view of at least one adjacent camera. The one or more ranging systems can be configured to transmit ranging data to a perception system for detecting objects of interest and the plurality of cameras can be configured to transmit image data to the perception system for classifying the objects of interest.
Dynamic Sensor Selection For Self-Driving Vehicles
- San Francisco CA, US David Rice - Pittsburgh PA, US Scott Boehmke - Pittsburgh PA, US Carl Wellington - Pittsburgh PA, US
International Classification:
B60R 16/023 G01C 21/20 G05D 1/00 B60W 50/023
Abstract:
A self-driving vehicle (SDV) can operate by analyzing sensor data to autonomously control acceleration, braking, and steering systems of the SDV along a current route. The SDV includes a number of sensors generating the sensor data and a control system to detect conditions relating to the operation of the SDV, such as vehicle speed and local weather, select a set of sensors based on the detected conditions, and prioritize the sensor data generated from the selected set of sensors to control aspects relating to the operation of the SDV.
- San Francisco CA, US Carl Knox Wellington - Pittsburgh PA, US David C. Driscoll - Pittsburgh PA, US
International Classification:
G02B 5/20 H04N 9/04 H01L 27/146
Abstract:
Image capture devices can include an image sensor, a color filter array, and an image processor. The image sensor can include an array of sensor elements configured to detect incoming light provided incident to a surface of the image sensor. The color filter array can be positioned adjacent to the image sensor for filtering the incoming light provided incident to the surface of the image sensor. The color filter array can include an array of filter elements including a plurality of clear filter elements and a plurality of color-sensitive filter elements. The plurality of color-sensitive filter elements can include at least one first color-sensitive filter element sensitive to a first band of the visible color spectrum and at least one second color-sensitive filter element sensitive to a second band of the visible color spectrum different than the first band.