# US 12,110,075 B2 · Providing a prediction of a radius of a motorcycle turn > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,110,075 B2 - Document ID: US12110075B2 - Status: Granted - Kind: B2 - Application number: 17/817,936 - Filed: 2022-08-05 - Published: 2023-02-09 - Granted: 2024-10-08 - Earliest claimed: 2021-08-05 - Assignees: Autobrains Technologies Ltd - Applicants: Autobrains Technologies Ltd - Inventors: Karina Odinaev; Igal Raichelgauz - Web page: https://patentgrep.com/patent/US12110075B2 ## CPC - B62J 45/00: Electrical equipment arrangements specially adapted for use as accessories on cycles, not otherwise provided for - B62J 45/20: Cycle computers as cycle accessories - B60W 30/18145: {Cornering} - B60W 40/072: Curvature of the road - B60W 50/0097: {Predicting future conditions} - B62J 27/00: Safety equipment - B62J 50/21: intended to provide information to rider or passenger - G05D 1/0212: {with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287)} - G05D 1/646: Following a predefined trajectory, e.g. a line marked on the floor or a flight path - B60W 2300/36: Cycles; Motorcycles; Scooters - B60Y 2200/12: Motorcycles, Trikes; Quads; Scooters - B62J 50/20: Information-providing devices - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 20/00: Machine learning - B62J: CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - B60Y: INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for providing a prediction of a radius of a motorcycle turn, the method may include determining that the motorcycle is about to turn; predicting values of multiple radius of turn impacting (RTI) parameters; wherein the multiple RTI parameters are selected out of a group of parameters, wherein the selection was made during a machine learning training process, and the group of parameters comprises motorcycle kinematic parameters; determining, based on the determined values of the multiple RTI parameters, the estimated radius of the motorcycle turn; and performing a driving related operation based on the estimated radius of the motorcycle turn. ## Claims ### Claim 1 A method for providing a prediction of a radius of a motorcycle turn, the method comprises: determining that the motorcycle is about to turn; predicting values of multiple radius of turn impacting (RTI) parameters; wherein the multiple RTI parameters are selected out of a group of parameters, wherein the selection was made during a machine learning training process, and the group of parameters comprises motorcycle kinematic parameters; determining, based on the determined values of the multiple RTI parameters, the estimated radius of the motorcycle turn; and performing a driving related operation based on the estimated radius of the motorcycle turn. ### Claim 2 (depends on 1) The method according to claim 1 comprising searching a matching concept structure out of multiple concept structures, wherein each concept structure comprises radius metadata indicative of the estimated radius of the motorcycle turn, and one or more unique reference combinations of values of the multiple RTI parameters, wherein the matching concept structure comprises a unique reference combination of values of the multiple RTI parameters that matches the determined values of the multiple RTI parameters. ### Claim 3 (depends on 2) The method according to claim 2 comprising performing at least one search iteration for finding the matching concept structure, wherein when a search iteration that utilized a sub-set of the multiple RTI parameters found two or more matching concept structures the executing another search iteration that utilizes the sub-set of the multiple RTI parameters and at least one additional RTI parameter. ### Claim 4 (depends on 2) The method according to claim 2 wherein the multiple concept structures are multiple clusters. ### Claim 5 (depends on 2) The method according to claim 2 wherein at least some of the multiple concept structures are associated with a safety parameter, wherein the performing of the driving related operation is responsive to the safety parameter. ### Claim 6 (depends on 5) The method according to claim 5 wherein a safety parameter associated with a concept structure is determined during the machine learning training process when a certain radius of turn consistently is associated with outcomes of a same safety level. ### Claim 7 (depends on 2) The method according to claim 2 comprising generating an alert when a matching concept structure is tagged as dangerous. ### Claim 8 (depends on 1) The method according to claim 1 wherein the performing of the driving related operation comprising providing a driver perceivable indication about a projected trajectory of the motorcycle. ### Claim 9 (depends on 1) The method according to claim 1 wherein the performing of the driving related operation comprises providing a driver perceivable indication about a projected trajectory of the motorcycle. ### Claim 10 (depends on 1) The method according to claim 1 wherein the performing of the driving related operation comprises displaying to the driver a projected trajectory of the motorcycle within an environment of the motorcycle. ### Claim 11 (depends on 10) The method according to claim 10 wherein the projected trajectory of the motorcycle within an environment of the motorcycle is taken from a bird eye view. ### Claim 12 (depends on 1) The method according to claim 1 wherein the group of parameters comprises environmental parameters. ### Claim 13 A non-transitory computer readable medium for providing a prediction of a radius of a motorcycle turn, the non-transitory computer readable medium comprises: determining that the motorcycle is about to turn; predicting values of multiple radius of turn impacting (RTI) parameters; wherein the multiple RTI parameters are selected out of a group of parameters, wherein the selection was made during a machine learning training process, and the group of parameters comprises motorcycle kinematic parameters; determining, based on the determined values of the multiple RTI parameters, the estimated radius of the motorcycle turn; and performing a driving related operation based on the estimated radius of the motorcycle turn. ### Claim 14 (depends on 13) The non-transitory computer readable medium according to claim 13 that stores instructions for searching a matching concept structure out of multiple concept structures, wherein each concept structure comprises radius metadata indicative of the estimated radius of the motorcycle turn, and one or more unique reference combinations of values of the multiple RTI parameters, wherein the matching concept structure comprises a unique reference combination of values of the multiple RTI parameters that matches the determined values of the multiple RTI parameters. ### Claim 15 (depends on 14) The non-transitory computer readable medium according to claim 14 that stores instructions for performing at least one search iteration for finding the matching concept structure, wherein when a search iteration that utilized a sub-set of the multiple RTI parameters found two or more matching concept structures the executing another search iteration that utilizes the sub-set of the multiple RTI parameters and at least one additional RTI parameter. ### Claim 16 (depends on 14) The non-transitory computer readable medium according to claim 14 wherein the multiple concept structures are multiple clusters. ### Claim 17 (depends on 14) The non-transitory computer readable medium according to claim 14 wherein at least some of the multiple concept structures are associated with a safety parameter, wherein the performing of the driving related operation is responsive to the safety parameter. ### Claim 18 (depends on 17) The non-transitory computer readable medium according to claim 17 wherein a safety parameter associated with a concept structure is determined during the machine learning training process when a certain radius of turn consistently is associated with outcomes of a same safety level. ### Claim 19 (depends on 14) The non-transitory computer readable medium according to claim 14 that stores instructions for generating an alert when a matching concept structure is tagged as dangerous. ### Claim 20 (depends on 13) The non-transitory computer readable medium according to claim 13 that stores instructions for providing a driver perceivable indication about a projected trajectory of the motorcycle.