Patents by Inventor John Redford
John Redford has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20220297709Abstract: Herein, a “perception statistical performance model” (PSPM) for modeling a perception slice of a runtime stack for an autonomous vehicle or other robotic system may be used e.g. for safety/performance testing. A PSPM is configured to: receive a computed perception ground truth t; determine from the perception ground truth t, based on a set of learned parameters, a probabilistic perception uncertainty distribution of the form p(e|t), p(e|t,c), in which p(e|t,c) denotes the probability of the perception slice computing a particular perception output e given the computed perception ground truth t and the one or more confounders c, and the probabilistic perception uncertainty distribution is defined over a range of possible perception outputs, the parameters learned from a set of actual perception outputs generated using the perception slice to be modeled, wherein each confounder is a variable of the PSPM whose value characterized a physical condition on which p(e|t,c) depends.Type: ApplicationFiled: August 21, 2020Publication date: September 22, 2022Applicant: Five AI LimitedInventors: John Redford, Simon Walker, Benedict Peters, Sebastian Kaltwang, Blaine Rogers, Jonathan Sadeghi, James Gunn, Torron Elson, Adam Charytoniuk
-
Publication number: 20220289218Abstract: Herein, a “perception statistical performance model” (PSPM) for modelling a perception slice of a runtime stack for an autonomous vehicle or other robotic system may be used e.g. for safety/performance testing. A first PSPM is configured to: receive a computed perception ground truth; determine from the perception ground truth, based on a set of learned parameters, a probabilistic perception uncertainty distribution, the parameters learned from a set of actual perception outputs generated using the perception slice to be modelled, in order to compute a first time series of perception outputs. A second time series of perception outputs is computed using a second PSPM for modelling a second perception slice of the runtime stack, the first PSPM learned from data of a first sensor modality of the perception slice and the time series, and the second PSPM learned independently thereof from data of a second sensor modality of the second perception slice and the second time series.Type: ApplicationFiled: August 21, 2020Publication date: September 15, 2022Applicant: Five AI LimitedInventors: John Redford, Sebastian Kaltwang, Sina Samangooei, Blaine Rogers
-
Publication number: 20220269279Abstract: Herein, a “perception statistical performance model” (PSPM) for modelling a perception slice of a runtime stack for an autonomous vehicle or other robotic system may be used e.g. for safety/performance testing. A PSPM is configured to receive a computed perception ground truth, and determine from the perception ground truth, based on a set of learned parameters, a probabilistic perception uncertainty distribution, the parameters learned from a set of actual perception outputs generated using the perception slice to be modelled. A simulated scenario is run based on a time series of such perception outputs (with modelled perception errors), but can also be re-run based on perception ground truths directly (without perception errors). This can, for example, be way to ascertain whether perception error was the cause of some unexpected decision within the planner, by determining whether such a decision is also taken in the simulated scenario when perception error is “switched off”.Type: ApplicationFiled: August 21, 2020Publication date: August 25, 2022Applicant: Five AI LimitedInventors: John Redford, Benedict Peters, Simon Walker
-
Patent number: 11403774Abstract: A method of annotating road images, the method comprising implementing, at an image processing system, the following steps: receiving a time sequence of two dimensional images as captured by an image capture device of travelling vehicle; processing the images to reconstruct, in three-dimensional space, a path travelled by the vehicle; using the reconstructed vehicle path to determine expected road structure extending along the reconstructed vehicle path; and generating road annotation data for marking at least one of the images with an expected road structure location, by performing a geometric projection of the expected road structure in three-dimensional space onto a two-dimensional plane of that image.Type: GrantFiled: March 13, 2019Date of Patent: August 2, 2022Assignee: Five AI LimitedInventors: Thomas Westmacott, Brook Roberts, John Redford
-
Publication number: 20220172390Abstract: A computer-implemented method of perceiving structure in an environment comprises steps of: receiving at least one structure observation input pertaining to the environment; processing the at least one structure observation input in a perception pipeline to compute a perception output; determining one or more uncertainty source inputs pertaining to the structure observation input; and determining for the perception output an associated uncertainty estimate by applying, to the one or more uncertainty source inputs, an uncertainty estimation function learned from statistical analysis of historical perception outputs.Type: ApplicationFiled: March 23, 2020Publication date: June 2, 2022Applicant: Five AI LimitedInventors: John Redford, Sebastian Kaltwang, Jonathan Sadeghi, Torran Elson
-
Patent number: 11308368Abstract: An image processing technique is presented using a hierarchical image model. The technique may be used as a precursor to subsequent image processing, to fix detected images in a post processing stage or as a segmentation or classification stage. The techniques may also be applied to super resolution. In a first layer of the hierarchical image model, each observed pixel of the image has a representation allocated to one or more input node. A set of the input nodes are assigned to a hidden node of a second layer, and a duplicate set of input nodes of the first layer is assigned to a duplicate of the hidden node in the second layer. In this way, a dense latent tree is formed in which a subtree is duplicated. Variables are assigned to the input nodes, the hidden node and the duplicate nodes and recurringly modified to process the image. Belief propagation messages may be utilised to recursively modify the variables. An image processing system using the method is described.Type: GrantFiled: May 17, 2019Date of Patent: April 19, 2022Assignee: Five AI LimitedInventors: Sebastian Kaltwang, John Redford
-
Publication number: 20210364320Abstract: In one aspect, a vehicle localization system implements the following steps: receiving a predetermined road map; receiving at least one captured image from an image capture device of a vehicle; processing, by a road detection component, the at least one captured image, to identify therein road structure for matching with corresponding structure of the predetermined road map, and determine a location of the vehicle relative to the identified road structure; and using the determined location of the vehicle relative to the identified road structure to determine a location of the vehicle on the road map, by matching the road structure identified in the at least one captured image with the corresponding road structure of the predetermined road map.Type: ApplicationFiled: March 13, 2019Publication date: November 25, 2021Applicant: Five Al LimitedInventors: Lars Mennen, John Redford
-
Publication number: 20210342600Abstract: A method of annotating frames of a time sequence of frames captured by at least one travelling vehicle comprises, in a frame processing system: determining a three-dimensional (3D) road model for an area captured in the time sequence of frames; receiving first annotation data denoting a known 3D location of a moving object for a first frame of the time sequence of frames; and automatically generating second annotation data for marking an expected moving object location in at least a second frame of the time sequence of frames, by assuming the moving object moves along an expected path determined from the known 3D location and the 3D road model.Type: ApplicationFiled: September 26, 2019Publication date: November 4, 2021Applicant: Five Al LimitedInventors: THOMAS WESTMACOTT, Joel Jakubovic, John Redford, Robert Chandler
-
Publication number: 20210232851Abstract: In one aspect, hierarchical image segmentation is applied to an image formed of a plurality of pixels, by classifying the pixels according to a hierarchical classification scheme, in which at least some of those pixels are classified by a parent level classifier in relation to a set of parent classes, each of which is associated with a subset of child classes, and each of those pixels is also classified by at least one child level classifier in relation to one of the subsets of child classes, wherein each of the parent classes corresponds to a category of visible structure, and each of the subset of child classes associated with it corresponds to a different type of visible structure within that category.Type: ApplicationFiled: June 6, 2019Publication date: July 29, 2021Applicant: Five Al LimitedInventors: John Redford, Sina Samangooei
-
Publication number: 20210224619Abstract: An image processing technique is presented using a hierarchical image model. The technique may be used as a precursor to subsequent image processing, to fix detected images in a post processing stage or as a segmentation or classification stage. The techniques may also be applied to super resolution. In a first layer of the hierarchical image model, each observed pixel of the image has a representation allocated to one or more input node. A set of the input nodes are assigned to a hidden node of a second layer, and a duplicate set of input nodes of the first layer is assigned to a duplicate of the hidden node in the second layer. In this way, a dense latent tree is formed in which a subtree is duplicated. Variables are assigned to the input nodes, the hidden node and the duplicate nodes and recurringly modified to process the image. Belief propagation messages may be utilised to recursively modify the variables. An image processing system using the method is described.Type: ApplicationFiled: May 17, 2019Publication date: July 22, 2021Applicant: Five Al LimitedInventors: Sebastian Kaltwang, John Redford
-
Publication number: 20210049780Abstract: A method of annotating road images, the method comprising implementing, at an image processing system, the following steps: receiving a time sequence of two dimensional images as captured by an image capture device of travelling vehicle; processing the images to reconstruct, in three-dimensional space, a path travelled by the vehicle; using the reconstructed vehicle path to determine expected road structure extending along the reconstructed vehicle path; and generating road annotation data for marking at least one of the images with an expected road structure location, by performing a geometric projection of the expected road structure in three-dimensional space onto a two-dimensional plane of that image.Type: ApplicationFiled: March 13, 2019Publication date: February 18, 2021Applicant: Five AI LimitedInventors: Tom Westmacot, Brook Roberts, John Redford
-
Patent number: 10241788Abstract: An apparatus including a queue configured to store a plurality of instructions and state information indicating whether each instruction of the plurality of instructions can be performed independently of older pending instructions; and a state-selection circuit configured to set a state information of each instruction of the plurality of instructions in view of an older pending instruction in the queue.Type: GrantFiled: October 31, 2014Date of Patent: March 26, 2019Assignee: Avago Technologies International Sales Pte. LimitedInventors: Tariq Kurd, John Redford
-
Publication number: 20180268321Abstract: An initial map corresponding to a physical event space may be modified to include a plurality of tenant space segments disposed within a boundary corresponding to the physical event space. Particular tenant space segments may be reserved by event tenants and associated with information descriptive of the event tenants. The customized map may be provided to one or more users of the public (e.g., attendees of the event).Type: ApplicationFiled: September 1, 2016Publication date: September 20, 2018Inventors: Thomas James Leafty, Bradley John Redford
-
Patent number: 10009760Abstract: A method for providing a communication device with credentials to enable it to access communication resources provided by a network operator, the method comprising storing, on the communication device, an indication of (i) an identity associated with the communication device; and (ii) an identity associated with a provisioning agent, transmitting, from the communication device to a communication network, a registration request that identifies the communication device and the provisioning agent, the provisioning agent providing, in response to the registration request, credentials to enable the communication device to access communication resources provided by a network operator and transmitting said credentials from the communication network to the communication device.Type: GrantFiled: April 23, 2015Date of Patent: June 26, 2018Assignee: Huawei Technologies Co., LtdInventor: John Redford
-
Patent number: 9841974Abstract: A processor including a register file having a plurality of registers, and configured for out-of-order instruction execution, further includes a renamer unit that produces generation numbers that are associated with register file addresses to provide a renamed version of a register that is temporally offset from an existing version of that register rather than assigning a non-programmer-visible physical register as the renamed register.Type: GrantFiled: October 31, 2014Date of Patent: December 12, 2017Assignee: Avago Technologies General IP (Singapore) Pte. Ltd.Inventors: Sophie Wilson, John Redford, Tariq Kurd
-
Patent number: 9798542Abstract: A method and apparatus for zero overheard loops is provided herein. The method includes the steps of identifying, by a decoder, a loop instruction and identifying, by the decoder, a last instruction in a loop body that corresponds to the loop instruction. The method further includes the steps of generating, by the decoder, a branch instruction that returns execution to a beginning of the loop body, and enqueing, by the decoder, the branch instruction into a branch reservation queue concurrently with an enqueing of the last instruction in a reservation queue.Type: GrantFiled: October 31, 2014Date of Patent: October 24, 2017Assignee: Avago Technologies General IP (Singapore) Pte. Ltd.Inventors: Tariq Kurd, John Redford, Geoffrey Barrett
-
Patent number: 9710272Abstract: A processor including a register file having a plurality of registers, and configured for out-of-order instruction execution, further includes a renamer unit that produces generation numbers that are associated with register file addresses to provide a renamed version of a register that is temporally offset from an existing version of that register rather than assigning a non-programmer-visible physical register as the renamed register. The processor includes a small reset DHL Gshare branch prediction unit coupled to an instruction cache and configured to provide speculative addresses to the instruction cache.Type: GrantFiled: October 31, 2014Date of Patent: July 18, 2017Inventors: Sophie Wilson, John Redford, Geoffrey Barrett, Tariq Kurd
-
Publication number: 20170017892Abstract: The disclosed apparatus and methods include a reconfigurable sampling accelerator and a method of using the reconfigurable sampling accelerator, respectively. The reconfigurable sampling accelerator can be adapted to a variety of target applications. The reconfigurable sampling accelerator can include a sampling module, a memory system, and a controller that is configured to coordinate operations in the sampling module and the memory system. The sampling module can include a plurality of sampling units, and the plurality of sampling units can be configured to generate samples in parallel. The sampling module can leverage inherent characteristics of a probabilistic model to generate samples in parallel.Type: ApplicationFiled: October 15, 2014Publication date: January 19, 2017Applicant: ANALOG DEVICES, INC.Inventors: JEFFREY G. BERNSTEIN, DAVID WINGATE, JOHN REDFORD
-
Publication number: 20150309796Abstract: A processor including a register file having a plurality of registers, and configured for out-of-order instruction execution, further includes a renamer unit that produces generation numbers that are associated with register file addresses to provide a renamed version of a register that is temporally offset from an existing version of that register rather than assigning a non-programmer-visible physical register as the renamed register.Type: ApplicationFiled: October 31, 2014Publication date: October 29, 2015Applicant: Broadcom CorporationInventors: Sophie WILSON, John Redford, Tariq Kurd
-
Publication number: 20150309795Abstract: A method and apparatus for zero overheard loops is provided herein. The method includes the steps of identifying, by a decoder, a loop instruction and identifying, by the decoder, a last instruction in a loop body that corresponds to the loop instruction. The method further includes the steps of generating, by the decoder, a branch instruction that returns execution to a beginning of the loop body, and enqueing, by the decoder, the branch instruction into a branch reservation queue concurrently with an enqueing of the last instruction in a reservation queue.Type: ApplicationFiled: October 31, 2014Publication date: October 29, 2015Applicant: Broadcom CorporationInventors: Tariq KURD, John REDFORD, Geoffrey BARRETT