Different drivers may prefer different performance characteristics from the same vehicle. One driver, for example, may prefer performance characteristics that emphasize fuel economy. Another driver may prefer performance characteristics that emphasize response and handling.
As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention that may be embodied in various and alternative forms. The figures are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present invention.
Introduction
The increasing intelligence and autonomy of automotive vehicles may significantly alter the customer driving experience. The growing connectivity of vehicles via digital communications, proliferation of navigation and road information systems, and advancements in computing and inexpensive sensor technology create numerous opportunities to improve vehicle performance by incorporating the wealth of information about driving conditions. The customization of vehicle response to individual customer preferences is also of significant interest.
In
The DAS 10 may cause the customization of vehicle powertrain response to driver preferences. These preferences may be communicated by the driver via the SDS 18, or learned over time and proactively suggested to the driver by the vehicle 12. The SDS 18 processes driver voice commands and other driver-supplied information. The information filter 20 may combine information from vehicle systems (e.g., information from any of the vehicle control modules or sensors on-board the vehicle), navigation and road information system, or wireless Internet to change the strategy parameters in the PCM 32. The information filter 20 may examine the direct driver inputs (e.g., inputs indicative of the immediate driver preferences), information about the present road conditions and other information to determine the best performance mode at any given time.
The DAS 10 may change powertrain performance mode, for example, between sport mode, normal mode, comfort mode, luxury mode and fuel economy mode based on driver preferences, for example, communicated or confirmed via voice commands. In the fuel economy mode, powertrain operation is configured to enhance fuel economy with some potential degradation in acceleration performance, while the sport mode enhances acceleration performance and vehicle responsiveness. The so-called normal mode is an intermediate mode, which is configured to balance vehicle fuel economy and acceleration performance attributes. The comfort or luxury mode may optimize powertrain smoothness to enhance driver comfort. The DAS 10 may also have a proactive performance mode advisory function to recommend a performance mode to the driver depending on the observations of recent driver actions as determined through data collected from a collection of vehicle and non-vehicle sources, as well as knowledge of past driver actions and preferences.
Spoken Dialog System
The SDS 18 may use verbal interaction between the driver and the vehicle 12 to avoid the hazards of look away events, to make the DAS 10 easy to use, and to save space on the dashboard.
Operating mode recommendations and the current operating mode may be computed in the vehicle systems 26 and passed to the SDS 18 on a periodic basis (e.g., about every 10 seconds). When the recommended mode differs from the current mode, the SDS 18 may initiate a verbal exchange with the driver. The information filter 20 may ensure that verbal interactions with the driver take place at appropriate times, such as when a driver response is necessary, when the driver is able to make a decision, or when the driving environment is suitable. It may also ensure that requests are not made too frequently.
If the recommended performance mode differs from the actual performance mode, the information filter 20 may initiate changing the mode by suggesting the recommended mode to the driver. The decision to initiate may be based on the level of certainty that the recommended mode would be helpful, the amount of time passed since the last recommendation was made, learned driver preferences from the user profile database 22, and/or contextual information from sensors and the Internet.
The approach used to determine the recommended performance mode setting is presented in detail below, but from the perspective of the SDS 18, the intent is to issue recommendations when it is appropriate for the driver to receive a recommendation. The information filter 20 makes sure that the driver does not receive recommendations too frequently causing distraction, frustration or dissatisfaction with the DAS 10.
To issue a recommendation, the information filter 20 sends a message to the dialog system 18 and then waits for a response. Upon receiving the message, the dialog system 18 creates a text string containing the words the driver should hear, such as “Would you like to switch to economy mode? I think you might get better fuel economy.” This string is then sent in a message to the TTS module 16, and the dialog system 18 waits for a response from the driver.
Upon receiving the text string, the TTS module 16 creates audible spoken words corresponding to the words in the string. The driver upon hearing the words formulates a response which is likely to be “yes” or “no,” but could be something more unexpected like “What is a performance mode?” or “Ask me later.”
The ASR module 14 detects the driver's response and converts it into a text string which it sends to the dialog system 18 in a message. The dialog system 18 creates an appropriate response which it sends to the TTS module 16, and then sends a message containing the meaning of the driver's response to the information filter 20. Based on the driver's response, the information filter 20 will either send a message to the PCM 32 to change the performance mode or not.
It is assumed that it is better to use an SDS that approximates conversational speech than one that uses individual utterances to move through a menu hierarchy. A conversational approach may have several advantages including that it is easier, more comfortable and more convenient to use than a hierarchical system. There are also advantages related to performance of the system such as better recognition. Either type (or a different type) of system, however, may be used.
The SDS 18 is capable of acting in either a proactive or directed manner. In the directed manner, the driver recognizes the need for a change in the mode, and requests the change from the SDS 18. This would begin with a statement from the driver such as “Please switch to economy mode.” The SDS 18 responds by saying “Ok, I will switch to economy mode.” The system then pauses for a second or so, in case a recognition error has occurred, in which case the driver would say something like “No, I said sport mode” and the SDS 18 says “Ok, I'll switch to sport mode.” After the switch is made, the SDS 18 may say “I've switched to sport operating mode.” Each time the driver directs the SDS 18, the change is logged and later compiled into the user profile database 22.
When the SDS 18 acts in proactive mode, it may try to make the driver aware of the possibility of changing the operating mode functionality when a good time to change operating mode occurs. It may say something like “Would you like to switch to fuel economy operating mode? I think you could save money on gas, but it might take longer to speed up.” If the driver were to say yes, the SDS 18 would respond by saying “I've switched to economy mode.” Based on the number of times the proactive mode has been used, the SDS 18 may say “You know, you can switch driving mode yourself Would you like me to explain?” The information filter 20 learns from the responses the driver gives, and bases future decisions on those responses.
Proactive Vehicle Performance Advisory System
A goal of the proactive vehicle performance advisory system may be to create a “driver-aware” vehicle that appeals to the driver by maximizing the driver's preferences of vehicle performance and allows the opportunity for performance personalization while leaving to the driver full responsibility and control of the vehicle 12. The system may estimate the current preferences of the driver in terms of acceleration performance versus fuel economy. They are later used to recommend to the driver a powertrain mode that is selected from a set of available performance mode configurations, such as sport, normal and fuel economy, and possibly including such aspects as throttle response and transmission shift performance.
Data captured from vehicle and non-vehicle sources can provide a significant resource to determine the characteristics and preferences of the driver. “Parameters” that may be considered include the accelerator pedal, vehicle speed, engine speed, driver commanded PRNDL or gear (select shift), actual transmission gear position, brake pedal position, brake pressure, and steering wheel angle (and derivatives of these signals) together with roadway speed limits, roadway type (multi-lane expressway, single lane county road, etc.), traffic volume, and patterns of these data may serve, in certain embodiments, as potential factors defining a driver's intent. Observation of these parameters individually or in various combinations over time may be used to characterize the driving style and determine the driver's performance preferences.
One may employ computational intelligence techniques (neural, fuzzy, clustering, etc.), hidden Markov methods, Baysian networks, or any other suitable/available technique to adopt the statistical concepts of common and special variation. We wish to identify unusual variations relative to the long term behaviour observed for the driver. Special variations (or anomalies) are those things that indicate a change in behaviour relative to the typical behaviour, such as a change in the location (e.g. mean value or variation) of a parameter (e.g., accelerator pedal position, etc.) that has been observed over a recent time horizon. These anomalies, when observed over a period of time, may indicate that the preferences of the driver have changed and that the system should now consider a new operating mode more consistent with the driver's current preferences. For example, a driver in city driving conditions may prefer highly responsive performance, but after entering the highway where they wish to maintain a constant speed, may prefer that the speed control system be activated. In this way, we are effectively learning a model of the driver and their preferences, which may change over time (time of day, day of week, etc.) and change due to different driving conditions (road type, weather, etc.)
Assume, for example, that the PCM 32 utilizes two driver input parameters, accelerator pedal position (available, for example, via CAN) and its derivative, and generates a covariance relative to an averaged version of these signals representing the driver's recent driving behaviour. It is then possible for the PCM 32 to generate a metric descriptive of the amount of variation in these parameters relative to the driver's typical behaviour utilizing a determinant of the resulting covariance matrix for instance. This determinant can then be compared to a set of thresholds generated based on the mean and variance of the determinant: an upper threshold equal to, for example, the mean plus three times the standard deviation of the determinant (indicative of change in driver behaviour in a more sporty or aggressive sense), and a lower threshold equal to, for example, the mean minus three times the standard deviation of the determinant (indicative of a change in driver behaviour in a more casual or cautious sense). Since there can be significant variability among individual drivers (and among driving styles of a specific driver over time), the thresholds may be allowed to change in relation to the average and variation of the metric (e.g., determinant) observed over time.
When the calculated metric exceeds the upper threshold(s) or falls below the lower threshold(s) for more than a calibratable period of time, the PCM 32 may conclude that the driver's behaviour has significantly changed relative to their typical behaviour (that is, a change in driver behaviour condition has occurred). The PCM 32 may then seek to alter a response of the vehicle 12 to driver inputs as discussed herein or forward this information to the DAS 10 so that a recommendation may be generated to inform the driver that a different performance mode may be more appropriate. While the above example is directed to accelerator and accelerator rate parameters, it could be applied to any combination of parameters in a similar manner, each with their own metrics and thresholds, which can be utilized individually as already described above or combined to form a composite metric having distinct adaptive thresholds. Also, the information filter 20 (or any other controller(s)/processor(s)) may perform the algorithms described above with reference to the PCM 32.
When anomalies in driver behaviour are observed, and a decision is made that the driver preferences have indeed changed, a decision may be made to determine the most appropriate mode to implement or recommend to the driver. This decision is based on the parameters which are applied to a learned rule base, driver intention model. As an example of this approach, assuming the use of driver torque request and vehicle speed parameters, the estimated driving style may be characterized as “abrupt” or “smooth” as manifested by the variability of the torque request. Similarly, driver's performance preference may be defined as “sporty” or “relaxed” based on vehicle speed and acceleration. A decision making mechanism assigns an appropriate performance mode to different combinations of, for example, the driving style, performance preference, and the average vehicle speed. The proactive vehicle performance advisory system may then, in certain embodiments, communicate its recommendation for the appropriate performance mode through the information filter 20 to the SDS 18. An affirmative response to the recommendation may cause, for example, the DAS 10 to instruct the PCM 32 to implement the recommended performance mode.
The mode selection decision logic may be summarized in the following example meta-rules:
The special variation being a change relative to the “typical” behaviour relies on threshold values determined by these typical behaviours. Since all drivers are unique, it is not likely that a set of fixed thresholds would be appropriate. Therefore, the transition thresholds may be updated continuously while the vehicle is driven to conform to the behaviours specific to each driver. Typical behaviour is then determined to be a situation in which a parameter lies within these thresholds. An anomaly is determined to be a situation in which a parameter lies outside of these thresholds for a sufficient period of time.
Powertrain Performance Modes
With the above discussed features, the vehicle 12 is able to assist the driver in selecting/implementing the most appropriate performance configuration, or alternatively to provide an easy to use voice controlled vehicle performance mode configuration interface. Some of the implementations discussed may rely on the selection from one of three available accelerator pedal transition mappings to affect the vehicle performance through a trade-off between acceleration responsiveness and fuel economy.
The sport mode setting may be configured to enhance acceleration performance feel by delivering more power for smaller accelerator pedal inputs. The driver may activate the sport mode setting when desiring all of the power of the vehicle to accelerate (e.g., when in a hurry, during passing, or in an emergency situation). The pedal translation map for the sport mode setting results in higher pedal sensitivity. (See
The comfort or luxury mode may be configured to enhance vehicle smoothness by reducing the accelerator pedal sensitivity over the normal range of accelerator inputs. In the fuel economy mode, a pedal translation map may be created to cause the transmission to up shift earlier for the same driver foot angle input as compared to the normal or sport modes. The intent is that the fuel economy mode is activated when the driver would like to reduce vehicle fuel consumption, extend vehicle driving range without refueling, or reduce fuel costs.
The normal mode is an intermediate performance mode that results from an intention to balance sportiness, fuel economy and luxury smoothness in a single mode. In the normal mode, the pedal to torque sensitivity may be less steep in certain ranges of the pedal travel.
Other implementations may additionally/alternatively alter the sensitivity of the steering system to steering inputs using known techniques. The implementation of, for example, sport mode may result in increased steering response for a given steering input while the implementation of comfort mode may result in decreased steering response for a given steering input. Other scenarios are also contemplated.
We described the development of a system for selecting a powertrain operating mode using, in certain embodiments, an SDS 18 and voice commands (manual input systems, however, are also contemplated). This hands-free/eyes-free capability when combined with the intelligence offered by the proactive vehicle performance advisory system is able to, for example, implement (or recommend) an accelerator pedal configuration which is tailored to the driver. Whether the driver values fuel economy or responsive acceleration, this system may address the diversity of drivers and driving styles with the objective of ultimately delivering improved customer satisfaction.
The algorithms disclosed herein may be deliverable to/implemented by a processing device, such as the DAS 10, information filter 20, PCM 32, etc., which may include any existing electronic control unit or dedicated electronic control unit, in many forms including, but not limited to, information permanently stored on non-writable storage media such as ROM devices and information alterably stored on writeable storage media such as floppy disks, magnetic tapes, CDs, RAM devices, and other magnetic and optical media. The algorithms may also be implemented in a software executable object. Alternatively, the algorithms may be embodied in whole or in part using suitable hardware components, such as Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), state machines, controllers or other hardware components or devices, or a combination of hardware, software and firmware components.
While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms of the invention. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various implementing embodiments may be combined to form further embodiments of the invention.
Number | Name | Date | Kind |
---|---|---|---|
4543569 | Karlstrom | Sep 1985 | A |
5081667 | Drori et al. | Jan 1992 | A |
5467070 | Drori et al. | Nov 1995 | A |
5513107 | Gormley | Apr 1996 | A |
5627510 | Yuan | May 1997 | A |
5635916 | Bucholtz et al. | Jun 1997 | A |
5655081 | Bonnell et al. | Aug 1997 | A |
5734336 | Smithline | Mar 1998 | A |
5776031 | Minowa et al. | Jul 1998 | A |
5828319 | Tonkin et al. | Oct 1998 | A |
5874889 | Higdon et al. | Feb 1999 | A |
5959540 | Walter | Sep 1999 | A |
6018291 | Marble et al. | Jan 2000 | A |
6133825 | Matsuoka | Oct 2000 | A |
6177866 | O'Connell | Jan 2001 | B1 |
6198996 | Berstis | Mar 2001 | B1 |
6263282 | Vallancourt | Jul 2001 | B1 |
6268804 | Janky et al. | Jul 2001 | B1 |
6271745 | Anzai et al. | Aug 2001 | B1 |
6282226 | Furukawa | Aug 2001 | B1 |
6434455 | Snow et al. | Aug 2002 | B1 |
6434486 | Studt et al. | Aug 2002 | B1 |
6438491 | Farmer | Aug 2002 | B1 |
6539078 | Hunt et al. | Mar 2003 | B1 |
6574734 | Colson et al. | Jun 2003 | B1 |
6590495 | Behbehani | Jul 2003 | B1 |
6668221 | Harter, Jr. et al. | Dec 2003 | B2 |
6679702 | Rau | Jan 2004 | B1 |
6690260 | Ashihara | Feb 2004 | B1 |
6737963 | Gutta et al. | May 2004 | B2 |
6754562 | Strege et al. | Jun 2004 | B2 |
6785542 | Blight et al. | Aug 2004 | B1 |
6810309 | Sadler et al. | Oct 2004 | B2 |
6853919 | Kellum | Feb 2005 | B2 |
6859718 | Fritz et al. | Feb 2005 | B2 |
6871145 | Altan et al. | Mar 2005 | B2 |
6906619 | Williams et al. | Jun 2005 | B2 |
6941194 | Dauner et al. | Sep 2005 | B1 |
7057501 | Davis | Jun 2006 | B1 |
7075409 | Guba | Jul 2006 | B2 |
7102496 | Ernst, Jr. et al. | Sep 2006 | B1 |
7124027 | Ernst, Jr. et al. | Oct 2006 | B1 |
7148790 | Aoyama et al. | Dec 2006 | B2 |
7161563 | Vitale et al. | Jan 2007 | B2 |
7173903 | Remboski et al. | Feb 2007 | B2 |
7194069 | Jones et al. | Mar 2007 | B1 |
7207041 | Elson et al. | Apr 2007 | B2 |
7228213 | Sakai et al. | Jun 2007 | B2 |
7246062 | Knott et al. | Jul 2007 | B2 |
7266438 | Kellum et al. | Sep 2007 | B2 |
7337113 | Nakagawa et al. | Feb 2008 | B2 |
7340332 | Underdahl et al. | Mar 2008 | B2 |
7356394 | Burgess | Apr 2008 | B2 |
7366892 | Spaur et al. | Apr 2008 | B2 |
7375620 | Balbale et al. | May 2008 | B2 |
7391305 | Knoll et al. | Jun 2008 | B2 |
7484008 | Gelvin et al. | Jan 2009 | B1 |
7565230 | Gardner et al. | Jul 2009 | B2 |
7602782 | Doviak et al. | Oct 2009 | B2 |
7783475 | Neuberger et al. | Aug 2010 | B2 |
7812712 | White et al. | Oct 2010 | B2 |
7826945 | Zhang et al. | Nov 2010 | B2 |
8050817 | Moinzadeh et al. | Nov 2011 | B2 |
8050863 | Trepagnier et al. | Nov 2011 | B2 |
8089339 | Mikan et al. | Jan 2012 | B2 |
8232864 | Kakiwaki | Jul 2012 | B2 |
8237554 | Miller et al. | Aug 2012 | B2 |
8258939 | Miller et al. | Sep 2012 | B2 |
8301108 | Naboulsi | Oct 2012 | B2 |
8305189 | Miller et al. | Nov 2012 | B2 |
8311722 | Zhang et al. | Nov 2012 | B2 |
20010021891 | Kusafuka et al. | Sep 2001 | A1 |
20020013650 | Kusafuka et al. | Jan 2002 | A1 |
20020031228 | Karkas et al. | Mar 2002 | A1 |
20020096572 | Chene et al. | Jul 2002 | A1 |
20020097145 | Tumey et al. | Jul 2002 | A1 |
20030004730 | Yuschik | Jan 2003 | A1 |
20030055643 | Woestemeyer et al. | Mar 2003 | A1 |
20030079123 | Mas Ribes | Apr 2003 | A1 |
20030217148 | Mullen et al. | Nov 2003 | A1 |
20030220725 | Harter, Jr. et al. | Nov 2003 | A1 |
20030231550 | Macfarlane | Dec 2003 | A1 |
20040046452 | Suyama et al. | Mar 2004 | A1 |
20040073367 | Altan et al. | Apr 2004 | A1 |
20040088205 | Geisler et al. | May 2004 | A1 |
20040124968 | Inada et al. | Jul 2004 | A1 |
20040176906 | Matsubara et al. | Sep 2004 | A1 |
20040227642 | Giles et al. | Nov 2004 | A1 |
20040236475 | Chowdhary | Nov 2004 | A1 |
20050021597 | Derasmo et al. | Jan 2005 | A1 |
20050033517 | Kondoh et al. | Feb 2005 | A1 |
20050125110 | Potter et al. | Jun 2005 | A1 |
20050134115 | Betts, Jr. et al. | Jun 2005 | A1 |
20050177635 | Schmidt et al. | Aug 2005 | A1 |
20050190039 | Aoyama | Sep 2005 | A1 |
20050193212 | Yuhara | Sep 2005 | A1 |
20050261816 | DiCroce et al. | Nov 2005 | A1 |
20060056663 | Call | Mar 2006 | A1 |
20060142917 | Goudy | Jun 2006 | A1 |
20060150197 | Werner | Jul 2006 | A1 |
20060156315 | Wood et al. | Jul 2006 | A1 |
20060220904 | Jarlengrip | Oct 2006 | A1 |
20060250224 | Steffel et al. | Nov 2006 | A1 |
20060293813 | Nou | Dec 2006 | A1 |
20070027595 | Nou | Feb 2007 | A1 |
20070050854 | Cooperstein et al. | Mar 2007 | A1 |
20070072616 | Irani | Mar 2007 | A1 |
20070100514 | Park | May 2007 | A1 |
20070103339 | Maxwell et al. | May 2007 | A1 |
20070255568 | Pennock | Nov 2007 | A1 |
20080070616 | Yun | Mar 2008 | A1 |
20080109653 | Yokohama | May 2008 | A1 |
20080148374 | Spaur et al. | Jun 2008 | A1 |
20080150683 | Mikan et al. | Jun 2008 | A1 |
20080275604 | Perry et al. | Nov 2008 | A1 |
20090030605 | Breed | Jan 2009 | A1 |
20090045928 | Rao et al. | Feb 2009 | A1 |
20090096596 | Sultan et al. | Apr 2009 | A1 |
20090167524 | Chesnutt et al. | Jul 2009 | A1 |
20090184800 | Harris | Jul 2009 | A1 |
20090195370 | Huffman et al. | Aug 2009 | A1 |
20090275281 | Rosen | Nov 2009 | A1 |
20090309709 | Bevacqua et al. | Dec 2009 | A1 |
20100004818 | Phelan | Jan 2010 | A1 |
20100007479 | Smith | Jan 2010 | A1 |
20100013596 | Kakiwaki | Jan 2010 | A1 |
20100030458 | Coughlin | Feb 2010 | A1 |
20100039224 | Okude et al. | Feb 2010 | A1 |
20100057586 | Chow | Mar 2010 | A1 |
20100075656 | Hawarter et al. | Mar 2010 | A1 |
20100097178 | Pisz et al. | Apr 2010 | A1 |
20100148923 | Takizawa | Jun 2010 | A1 |
20100178872 | Alrabady et al. | Jul 2010 | A1 |
20100191535 | Berry et al. | Jul 2010 | A1 |
20100191973 | Huntzicker et al. | Jul 2010 | A1 |
20100321203 | Tieman et al. | Dec 2010 | A1 |
20110009107 | Guba et al. | Jan 2011 | A1 |
20110071720 | Schondorf et al. | Mar 2011 | A1 |
20110071725 | Kleve et al. | Mar 2011 | A1 |
20110071734 | Van Wiemeersch et al. | Mar 2011 | A1 |
20110102146 | Giron | May 2011 | A1 |
20110105097 | Tadayon et al. | May 2011 | A1 |
20110106374 | Margol et al. | May 2011 | A1 |
20110112969 | Zaid et al. | May 2011 | A1 |
20110148574 | Simon et al. | Jun 2011 | A1 |
20110166748 | Schneider et al. | Jul 2011 | A1 |
20110213629 | Clark et al. | Sep 2011 | A1 |
20110215921 | Ayed et al. | Sep 2011 | A1 |
20110275321 | Zhou et al. | Nov 2011 | A1 |
20110295444 | Westra et al. | Dec 2011 | A1 |
20120041633 | Schunder et al. | Feb 2012 | A1 |
20120054036 | Nam et al. | Mar 2012 | A1 |
20120071140 | Oesterling et al. | Mar 2012 | A1 |
20120139760 | Bevacqua et al. | Jun 2012 | A1 |
20120157069 | Elliott et al. | Jun 2012 | A1 |
20120280786 | Miller et al. | Nov 2012 | A1 |
20120284702 | Ganapathy et al. | Nov 2012 | A1 |
20120293317 | Hanna et al. | Nov 2012 | A1 |
20120313768 | Campbell et al. | Dec 2012 | A1 |
20130005302 | Ozaki | Jan 2013 | A1 |
20130162421 | Inaguma et al. | Jun 2013 | A1 |
20130200999 | Spodak et al. | Aug 2013 | A1 |
Number | Date | Country |
---|---|---|
1863052 | Nov 2006 | CN |
101596895 | Dec 2009 | CN |
102007046270 | Apr 2009 | DE |
0449471 | Oct 1991 | EP |
0971463 | Jan 2000 | EP |
1095527 | May 2001 | EP |
2008195253 | Aug 2008 | JP |
2008303630 | Dec 2008 | JP |
WO0125572 | Apr 2001 | WO |
2009158469 | Dec 2009 | WO |
2012015403 | Feb 2013 | WO |
Entry |
---|
Autobiometrics, Com, US Distributor for ATRD Biometric Immobilizer, http://www.autobiometrics.com, Jul. 6, 2011. |
SALES@usasupremetech.com, In the U.S. a Car is Stolen Every 26 Seconds, The Wave of the Future, Biometrics Authentication, An Introduction. |
Ford Motor Company, “SYNC with Navigation System,” Owner's Guide Supplement, SYNC System Version 1 (Jul. 2007). |
Ford Motor Company, “SYNC,” Owners's Guide Supplement, SYNC System Version 1 (Nov. 2007). |
Ford Motor Company, “SYNC with Navigation System,” Owner's Guide Supplement, SYNC System Version 2 (Oct. 2008). |
Ford Motor Company, “SYNC,” Owner's Guide Supplement, SYNC System Version 2 (Oct. 2008). |
Ford Motor Company, “SYNC with Navigation System,” Owner's Guide Supplement, SYNC System Version 3 (Jul. 2009). |
Ford Motor Company, “SYNC,” Owner's Guide Supplement, SYNC System Version 3 (Aug. 2009). |
Kermit Whitfield, “A hitchhiker's guide to the telematics ecosystem,” Automotive Design & Production, Oct. 2003, http://findarticles.com, pp. 103. |
Juha Leino et al., Case Amazon: Ratings and Reviews as Part of Recommendations, RecSys '07, Oct. 19-20, 2007, pp. 137-140, Minneapolis, Minnesota, USA, Copyright 2007 ACM 978-1-59593-730-8/07/0010. |
Toine Bogers et al., Comparing and Evaluating Information Retrieval Algorithms for News Recommendation, RecSys '07, Oct. 19-20, 2007, 4 pgs., Minneapolis, Minnesota, USA, Copyright 2007 ACM 978-1-59593-730-08/07/0010. |
Mike Radmacher, Elicitation of Profile Attributes by Transparent Communication, RecSys '07, Oct. 19-20, 2007, pp. 199-202, Minneapolis, Minnesota, USA, Copyright 2007 ACM 978-1-59593-730-08/07/0010. |
Marco Tiemann et al., Ensemble Learning for Hybrid Music Recommendation, 2007, 2 pgs., Austrian Computer Society (OCG). |
J.J. Sandvig et al., Robustness of Collaborative Recommendation Based on Association Rule Mining, RecSys '07, Oct. 19-20, 2007, 7 pgs., Minneapolis, Minnesota, USA, Copyright 2007 ACM 978-1-59593-730-8/07/0010. |
Jill Freyne et al., Toward the Exploitation of Social Access Patterns for Recommendation, RecSys '07, Oct. 19-20, 2007, 4 pgs., Minneapolis, Minnesota, USA, Copyright 2007 ACM 978-1-59593-730-8/07/0010. |
Liu Qiao et al., Self-Supervised Learning Algorithm of Environment Recognition in Driving Vehicle, IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, vol. 26, No. 6, Nov. 1996, pp. 843-850. |
Yasuhiro Yokoi et al., Driving Pattern Prediction for an Energy Management System of Hybrid Electric Vehicles in a Specific Driving Course, The 30th Annual Conference of the IEEE Industrial Electronics Society, Nov. 2-6, 2004, Busan, Korea, pp. 1727-1732. |
Randy Allen Harris, Voice Interaction Design: Crafting the New Conversational Speech Systems (Morgan Kaufmann Series in Interactive Technologies); Morgan Kaufmann (Dec. 27, 2004), Chapters 3, 11 and 15, 65 pgs. |
It's What Makes a Subaru, a Subaru: Subaru Intelligent Drive (SI-DRIVE), http://drive2.subaru.com/Summer07—whatmakes.htm, Summer 2007, 2 pgs. |
Jeffrey M. O'Brien, The Race to Create a ‘Smart’ Google, CNN Money, Fortune Magazine, Nov. 27, 2006, http://money.cnn.com/magazines/fortune/fortune—archive/2006/11/27/8394347/, 4 pgs. |
I.V. Kolmanovsky et al., Speed Gradient Control of Nonlinear Systems and Its Applications to Automotive Engine Control, 2008 SICE, 8 pgs. |
Recommender System, Wikipedia, The Free Encyclopedia, Aug. 10, 2012, 5 pgs., https://secure.wikimedia.org/wikipedia/en/w/index.php?title=Recommender—system&oldid=201146474. |
Collaborative Filtering, Wikipedia, The Free Encyclopedia, Aug. 10, 2012, 7 pgs., https://secure.wikimedia.org/wikipedia/en/w/index.php?title=Collaborative—filtering&oldid=199820810. |
Number | Date | Country | |
---|---|---|---|
20120316699 A1 | Dec 2012 | US |