(12) INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT)
`
`(19) World Intellectual Property Organization
`International Bureau
`
`( 43) International Publication Date
`4 May 2006 (04.05.2006)
`
`PCT
`
`(51) International Patent Classification:
`B60W 50/08 (2006.01)
`B60W 40/02 (2006.01)
`B60W 40/10 (2006.01)
`G0SD 1102 (2006.01)
`B60W 40/08 (2006.01)
`
`(21) International Application Number:
`PCT/US2005/037918
`
`(22) International Filing Date: 21 October 2005 (21.10.2005)
`
`(25) Filing Language:
`
`(26) Publication Language:
`
`English
`
`English
`
`(30) Priority Data:
`10/972,082
`10/971,724
`10/971,725
`10/972,081
`10/971,718
`
`22 October 2004 (22.10.2004) us
`22 October 2004 (22.10.2004) us
`22 October 2004 (22.10.2004) us
`22 October 2004 (22.10.2004) us
`22 October 2004 (22.10.2004) us
`
`(71) Applicant (for all designated States except US): !ROBOT
`iiiiiiiiiiii
`CORPORATION [US/US]; 63 South Avenue, Burlington,
`MA 01803-4903 (US).
`
`(72) Inventors; and
`(75) Inventors/Applicants (for US only): ALLARD, James,
`R. [US/US]; 300 Hartman Road, Newton, MA 02159
`(US). BARRETT, David, S. [US/US]; 18 Glenwood
`Drive, Needham, MA 02192 (US). FILIPPOV, Mikhail
`[RU/US]; 276 Highland Avenue, Arlington, MA 02476
`(US). PACK, Robert, Todd [US/US]; 27 Vieckis Drive,
`
`- i
`
`---iiiiiiiiiiii
`--
`
`
`
`1111111111111111 IIIIII IIIII 11111111111111111111111111111111111 IIIII IIIII IIII 111111111111111 IIII
`
`
`
`
`
`(10) International Publication Number
`WO 2006/047297 A2
`Nashua, NH 03062 (US). SVENDSEN, Selma [BA/US];
`7 Cameron Road, Andover, MA 01810 (US).
`
`(74) Agents: JAGENOW, Andrew, L. et al.; Goodwin Procter
`LLP, Exchange Place, Boston, MA 02109 (US).
`
`(81) Designated States (unless otherwise indicated, for every
`kind of national protection available): AE, AG, AL, AM,
`AT, AU, AZ, BA, BB, BG, BR, BW, BY, BZ, CA, CH, CN,
`CO, CR, CU, CZ, DE, DK, DM, DZ, EC, EE, EG, ES, Fl,
`GB, GD, GE, GH, GM, HR, HU, ID, IL, IN, IS, JP, KE,
`KG, KM, KP, KR, KZ, LC, LK, LR, LS, LT, LU, LV, LY,
`MA, MD, MG, MK, MN, MW, MX, MZ, NA, NG, NI, NO,
`NZ, OM, PG, PH, PL, PT, RO, RU, SC, SD, SE, SG, SK,
`SL, SM, SY, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ,
`VC, VN, YU, ZA, ZM, ZW.
`
`(84) Designated States (unless otherwise indicated, for every
`kind of regional protection available): ARIPO (BW, GH,
`GM, KE, LS, MW, MZ, NA, SD, SL, SZ, TZ, UG, ZM,
`ZW), Eurasian (AM, AZ, BY, KG, KZ, MD, RU, TJ, TM),
`European (AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI,
`FR, GB, GR, HU, IE, IS, IT, LT, LU, LV, MC, NL, PL, PT,
`RO, SE, SI, SK, TR), OAPI (BF, BJ, CF, CG, CI, CM, GA,
`GN, GQ, GW, ML, MR, NE, SN, TD, TG).
`
`Published:
`without international search report and to be republished
`upon receipt of that report
`
`For two-letter codes and other abbreviations, refer to the "Guid(cid:173)
`ance Notes on Codes and Abbreviations" appearing at the begin(cid:173)
`ning of each regular issue of the PCT Gazette.
`
`- ---------------------------------------------
`iiiiiiiiiii -
`--iiiiiiiiiiii
`
`(54) Title: SYSTEMS AND METHODS FOR CONTROL OF A VEHICLE
`
`(57) Abstract: Systems and methods for autonomous control of a vehicle include interruptible, behavior-based, and selective con(cid:173)
`trol. Autonomous control is achieved by using actuators that interact with input devices in the vehicle. The actuators (e.g., linkages)
`iiiiiiiiiiii
`manipulate the input devices (e.g., articulation controls and drive controls, such as a throttle, brake, tie rods, steering gear, throttle
`lever, or accelerator) to direct the operation of the vehicle. Although operating autonomously, manual operation of the vehicle is
`possible following the detection of events that suggest manual control is desired. Subsequent autonomous control may be permitted,
`permitted after a prescribed delay, or prevented. Systems and methods for processing safety signals and/or tracking terrain features
`are also utilized by an autonomous vehicle.
`
`IPR2025-00943
`Tesla EX1025 Page 1
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`SYSTEMS AND METHODS FOR CONTROL OF A VEHICLE
`
`Related Applications
`
`[0001] The present application claims priority to and the benefit of U.S. Application Serial Nos.
`
`10/972,082, filed on October 22, 2004; 10/971,724, filed on October 22, 2004; 10/971,725, filed
`
`October 22, 2004; 10/972,081, filed October 22, 2004; and 10/971,718, filed October 22, 2004-
`
`5
`
`the disclosures of which are being incorporated by reference herein.
`
`Field of the Invention
`
`[0002] The present invention relates generally to control of unmanned ground vehicles and,
`
`more specifically, to variations in the control of unmanned ground vehicles in response to
`
`environmental changes or operator intervention.
`
`Background of the Invention
`
`[0003] Vehicles and equipment that operate with little or no operator intervention are desirable
`
`partly because they remove the operator from harm's way in dangerous applications and because
`
`they offer direct labor cost savings in commercial applications. In many instances, this limited
`
`intervention is exemplified by an operator removed from the confines of the vehicle itself and
`
`15
`
`placed in a location with a remote control device that interfaces with and controls the vehicle.
`
`In
`
`this configuration, however, the operator typically must directly and continuously monitor the
`
`vehicle and its surrounding environment, adjusting, for example, vehicle speed and direction, as
`
`needed. In particular, when a task is complex, the operator must carefully monitor the vehicle or
`
`equipment to the point where any simplification of the operator's tasks is negated by the high
`
`20
`
`level of concentration required to ensure the vehicle avoids obstacles, hazards, and other terrain
`
`features in its path, thereby preventing accidents. This requires considerable effort by the
`
`operator, a significant investment in skilled operator training, and places severe limitations on
`
`mission duration and objectives.
`
`[0004] In a typical environment, a vehicle can encounter any number of unforeseen hazards. A
`
`25
`
`vehicle can also create or exacerbate a hazard. In either case, there is the potential that the
`
`IPR2025-00943
`Tesla EX1025 Page 2
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 2 -
`
`vehicle may endanger persons or property. Accordingly, an operator generally pays particular
`
`attention to events that may result in dangerous conditions. This additional safety concern
`
`negatively affects mission effectiveness because it directs the operator's attention away from the
`
`particulars of the task the vehicle is performing. Additionally, an operator may become
`
`5
`
`overwhelmed by the degree of oversight and attention required and may fail to recognize one or
`
`more obstacles or hazards in the path of the vehicle, potentially resulting in an accident.
`
`[0005] From the foregoing, it is apparent that there is a direct need for efficient, autonomous
`
`control of a vehicle or equipment that relieves the operator of most, if not all, of operational
`
`oversight. The vehicle or equipment needs to accomplish its assigned tasks while compensating
`
`IO
`
`for the environment in an autonomous fashion but still be responsive to the attempts by an
`
`operator to assume control. The vehicle must also ensure the safety of the its surroundings.
`
`Summary of the Invention
`
`[0006] In one aspect, the invention relates to a method for control o:f a vehicle, the method
`
`including the steps of: identifying at least one input device in the vehicle, providing at least one
`
`15
`
`actuator associated with the at least one input device, and controlling the vehicle based at least in
`
`part on at least one of an interruptible autonomous scheme, a behavior based autonomous
`
`scheme, a selective scheme, and a safety scheme.
`
`[0007] In another aspect, the invention relates a system for control of a vehicle, the system
`
`including: means for controlling the vehicle, means for actuating tl1e vehicle control means, and
`
`20 means for controlling the vehicle based at least in part on at least one of an interruptible
`
`autonomous controller, a behavior based autonomous controller, a selective controller, and a
`
`safety controller.
`
`[0008] In one aspect, the present invention provides systems and methods for interruptible
`
`autonomous control of a vehicle. Although operating autonomously, an operator can override
`
`25
`
`the autonomous control to the extent necessary to, for example, adjust the progress of the
`
`vehicle. Mission effectiveness is increased because the operator is relieved from most, if not all,
`
`navigational oversight of the vehicle. Further, safety systems, typically running autonomously,
`
`are provided. This improves vehicle safety, reliability, and decreases or eliminates the need for
`
`manual intervention.
`
`IPR2025-00943
`Tesla EX1025 Page 3
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 3 -
`
`[0009] The invention features a method for interruptible autonomous control of a vehicle, where
`
`a disassociation between a vehicle's input devices and its associated actuators are detected. An
`
`input device may be an operator input device such as a drive control ( e.g. steering wheel, brake
`
`pedal, accelerator, or throttle,) or it may include a device connecting an operator input device to
`
`5
`
`the remainder of the drive chain of the vehicle, (e.g., a throttle lever, steering gear, tie rods, or
`
`other device that directs vehicle position or motion and that may not be directly manipulated by a
`
`human operator. In some embodiments, the input device is an articulation control that usually
`
`directs apparatus connected to the vehicle. In an autonomous vehicle, the actuator directly
`
`manipulates the linkage or is attached to the input device.
`
`10
`
`[0010] In certain embodiments, autonomous control is interrupted when a disassociation
`
`between the input device and its actuator is detected. For example, if the input device is a brake
`
`and an operator depresses the brake, the latter will separate from its actuator. The separation
`
`(i.e., disassociation) is detected and the autonomous control of the brake is discontinued. In
`
`other embodiments, autonomous control is reestablished after the operator ceases manipulating
`
`15
`
`the input device (e.g., removes his or her foot from the brake, thereby reassociating the control
`
`surface and the actuator). Different embodiments prevent the reestablishment of autonomous
`
`control. In either case, proximity sensors and strain gauges typically detect the disassociation
`
`and reassociation.
`
`[0011] The invention also features a method where the detection of a disassociation initiates a
`
`20
`
`shutdown sequence. In some embodiments, this is used to enhance operational safety.
`
`[0012] Another aspect of the invention includes a system for interruptible control of a vehicle.
`
`This system includes a controller, such as a microprocessor or microcontroller,
`
`in
`
`communication with the detectors and actuators, that manages the discontinuation and
`
`reestablishment of autonomous control. The controller acts in accordance with control policies
`
`25
`
`that characterize the behavior of the input device in different vehicle operational modes (e.g.,
`
`autonomous, manual). A further aspect of the invention includes a system that initiates and
`
`controls a shutdown sequence after detection of a disassociation between a control surface and an
`
`actuator.
`
`[0013] In another aspect, the present invention provides a system and method for behavior based
`
`30
`
`control of an autonomous vehicle. While operating autonomously, the vehicle is aware of its
`
`IPR2025-00943
`Tesla EX1025 Page 4
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 4 -
`
`surroundings, particularly the location and character of terrain features that may be obstacles.
`
`Because these terrain features can represent hazards to the vehicle, the vehicle preferably
`
`compensates by altering its trajectory or movement.
`
`[0014] The invention features a method for the behavior based control of an autonomous vehicle
`
`5
`
`where several behaviors are associated with the actuators that manipulate input devices that
`
`direct the vehicle. An input device may be an operator input device that directs at least part of
`
`the vehicle ( e.g., one or more of a steering wheel, handle, brake pedal, accelerator, or throttle).
`
`The input device also may be a device directly or indirectly connecting the operator input device
`
`to a controlled element (i.e., the object in the autonomous vehicle ultimately controlled by the
`
`10
`
`operator input device). For example, the operator input device may be a throttle, and the input
`
`device may be the throttle body. Although a human operator typically accesses and manipulates
`
`the operator input device, the input device need not be accessible or operable by the human
`
`operator.
`
`[0015] A behavior is a program that proposes an action based on sensor data, operator input, or
`
`15 mission goals. Actions are typically grouped into action sets, and the action sets are generally
`
`prioritized. The actions within an action set are termed" alternative actions," and each
`
`alternative action generally has a corresponding preference. The preferences allow for the
`
`ranking of the alternative actions.
`
`[0016] Multiple behaviors continuously propose actions to an arbiter. The arbiter continuously
`decides which behavior is expressed based on a weighted set of goals. The arbiter selects the
`
`20
`
`action set with the highest priority, and also selects the alternative action from within the selected
`
`action set with the highest corresponding preference. A behavior based system can include many
`
`behaviors and multiple arbiters, and multiple arbiters can be associated with an actuator.
`
`Multiple arbiters associated with an actuator are sometimes referred to as "stacked arbiters." An
`
`25
`
`actuator is typically a servo-system and transmission in physical contact with the existing input
`
`devices in the vehicle.
`
`[0017] In some embodiments, the behaviors characterize the operational mode of the vehicle.
`These modes include; manned operation, remote unmanned tele-operation, assisted remote tele(cid:173)
`
`operation, and autonomous unmanned operation. In the manned operation mode a vehicle
`
`30
`
`operator sits in the vehicle cockpit and drives the vehicle using its traditional command input
`
`IPR2025-00943
`Tesla EX1025 Page 5
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 5 -
`
`devices (e.g. steering wheel, brake, accelerator, throttle, etc.). In the remote unmanned tele(cid:173)
`
`operation mode a dismounted operator or an operator in a chase vehicle drives the unmanned
`
`vehicle from a safe stand off distance through a portable operator control unit that allows the
`
`operator to directly command the vehicle. In the assisted remote tele-operation mode, the
`
`5
`
`dismounted operator can engage "assistive behaviors" that facilitate mission execution. These
`
`assistive behaviors use the vehicles sensors, control system, and perception and localization
`
`subsystems to add short-term, safe, self-navigation functionality to the vehicle. Examples of
`
`assisted behaviors include active obstacle avoidance, circling in place and deploying payloads
`
`based on sensor input. Such an assist allows the operator to focus more on the mission and less
`
`IO
`
`on the continuous demand of driving. In the autonomous mode, the vehicle uses an arbitrated
`
`behavior based technique to perform a tactically significant mission. Examples of such missions
`
`include following a moving object at a fixed distance and travelling through a pre-recorded set of
`
`fixed GPS waypoints while actively performing obstacle avoidance.
`
`Each mode can include a
`
`set of alternative behaviors that the vehicle can take to accomplish its task. In some
`
`15
`
`embodiments, the alternative behaviors are ranked by priority or preference and an arbiter selects
`
`the behavior to be performed. The behavior can then operate the corresponding vehicle control
`
`accordingly.
`
`[0018) In some embodiments, the behaviors include trajectory sets and, in further embodiments,
`
`the behavior includes adjusting the translational velocity, or rotational velocity, or both, of the
`
`20
`
`autonomous vehicle, typically in response to data received fro:m sensors or a map of terrain
`
`features located around the vehicle.
`
`[0019) Another aspect of the invention includes a system for behavior based operation of an
`
`autonomous vehicle that includes a controller, such as a microprocessor or microcontroller, that
`
`provides the host environment for the multiple resident behavior programs and the arbiter
`
`25
`
`program and, in response to the behaviors, operates one or more vehicle controls using actuators.
`
`The controller also communicates with one or more localization or perception sensors, and using
`
`one or more localization and perception behaviors builds a vehicle centric terrain feature map.
`
`The controller runs the behavior system and specifies the actions to be performed.
`
`[0020) In yet another aspect, the present invention provides a system and method for multi-
`
`30 model control of an autonomous vehicle. Depending on, for example, the task to be completed,
`
`IPR2025-00943
`Tesla EX1025 Page 6
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`-6-
`
`the vehicle can operate in different modes. The different operational modes allow the vehicle to
`
`compensate for variations in the task and changes in the environment around the vehicle. This
`
`increases mission effectiveness and promotes the safe operation of the vehicle.
`
`[0021] The invention features a method for selective control of a vehicle in response to receiving
`
`5
`
`a mode select command. In some embodiments, the mode select command includes one or more
`
`of a manned operation, remote unmanned tele-operation, assisted remote unmanned tele(cid:173)
`
`operations, and autonomous unmanned operation. After receipt of the mode select command, a
`
`specific representative set of vehicle control behaviors are enabled that allow operation in that
`
`specific mode.
`
`10
`
`[0022] Another aspect of the invention includes a system for selective control of a vehicle that
`
`includes a receiver for receiving the mode select command. A controller, such as a
`
`microprocessor or microcontroller, communicates with the receiver and executes a vehicle
`
`control program. This controller, such as a microprocessor or microcontroller, provides the host
`
`environment for the multiple resident behavior programs and the arbiter program, and, in
`
`15
`
`response to the behaviors, operates one or more vehicle controls using actuators.
`
`[0023] In still another aspect, the present invention provides a system and method for processing
`
`a safety signal in an autonomous vehicle. While operating unmanned, the vehicle uses its on(cid:173)
`
`board local area sensors and its perceptual context software to detect the presence of unsafe
`
`conditions. The vehicle also receives and acts on emergency signals sent by the operator. In
`
`20
`
`either case, processing of the detected or signaled information leads, in some embodiments, to
`
`the manipulation of vehicle input devices in a manner to ensure the proper response to the
`
`detected or signaled information.
`
`[0024] Given the importance of safe vehicle operation, some embodiments of the invention
`
`include redundant communication paths for conveying the detected or signaled information.
`
`25
`
`These communication paths may include; a hard-wired electrical safety circuit, a firmware based
`
`dedicated microprocessor actuator control network, and a collection of software based fault
`
`detection code residing in the main vehicle control computer. Operating in parallel, these
`
`multiple communication paths provide a robust method to ensure that detected or signaled safety
`
`information is conveyed and acted on.
`
`IPR2025-00943
`Tesla EX1025 Page 7
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`-7-
`
`[0025] Another aspect of the invention includes a system for processing a safety signal. This
`
`system includes a controller, such as a microprocessor or microcontroller, in communication
`
`with actuators via a transmitter using multiple communication links. In response to detected or
`signaled information, the controller, in certain embodiments, instructs the actuators to manipulate
`
`s
`
`one or more vehicle input devices, typically using linkages, to affect a safe response to a
`
`potentially (or actually) unsafe condition. In various embodiments, the controller acts in
`
`accordance with control policies that characterize the behavior of the input device in different
`
`vehicle operational modes (e.g., autonomous, manual).
`
`[0026] Although operating autonomously, an operator can override the autonomous control to
`
`10
`
`the extent necessary to, for example, adjust the progress of the vehicle. Tactically significant
`
`mission effectiveness is increased because the operator is relieved from most, if not all, safety
`
`oversight of the vehicle. Further, safety systems, typically running autonomously, are provided.
`
`This improves vehicle safety, reliability, and decreases or eliminates the need for manual
`
`intervention.
`
`15
`
`[0027] In still another aspect, the present invention provides a system and method for tracking
`
`one or more terrain features by an autonomous vehicle. While operating autonomously, the
`
`vehicle uses its on-board local area sensors and its perceptual context software to determine the
`
`location and character of terrain features, which may be obstacles or targets. Because these
`
`terrain features can represent hazards or targets to the vehicle, the vehicle preferably
`
`20
`
`compensates by altering its trajectory or movement.
`
`[0028] The invention features a method for tracking terrain features using localization and
`
`perception. sensors. Localization sensors determine the location and orientation of the
`
`autonomous vehicle. In some embodiments, the localization sensors include sensors to measure
`
`pitch, roll, and yaw. Other embodiments include an inertial navigation system, a compass, a
`
`25
`
`global positioning system, or an odometer. Perception sensors assess the environment about the
`
`autonomous vehicle. In some embodiments, the perception sensors include a LIDAR (Light
`
`Detection and Ranging, or laser imaging, system), stereo vision system, infrared vision system,
`
`radar system, or a sonar system.
`
`(0029] Using these sensors, embodiments of the invention compute the location of all relevant
`
`30
`
`terrain features detected and store the location information in memory. When the outputs of the
`
`IPR2025-00943
`Tesla EX1025 Page 8
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 8 -
`
`sensors change, the locations are updated accordingly. To conserve memory, cope with faulty
`
`sensor data, and accommodate moving objects, some embodiments discard older location data
`
`deemed "stale" due to the passage of time or distance traveled.
`
`In response to the determining
`
`up-to-date locations of terrain features, the autonomous vehicle adjusts its trajectory. In certain
`
`5
`
`embodiments, adjusting the trajectory includes selecting a preferred trajectory from a group of
`
`several ranked alternative trajectories.
`
`[0030] Another aspect of the invention includes a systelil for tracking terrain features that
`
`includes one or more controllers, such as microprocessors or microcontrollers that communicates
`
`with the localization and perception sensors. The controllers also communicate with a vehicle-
`
`IO
`
`based memory for storing location information. In some embodiments, the system includes
`
`adjustment logic that operates to adjust the trajectory of the autonomous vehicle in response to
`
`the presence of terrain features.
`
`[0031] Other aspects and advantages of the present invention will become apparent from the
`
`following detailed description, taken in conjunction with the accompanying drawings, illustrating
`
`15
`
`the principles of the invention by way of example only.
`
`Brief Description of the Drawings
`
`[0032] The foregoing and other objects, features, and advantages of the present invention, as
`
`well as the invention itself, will be more fully understood from the following description of
`
`various embodiments, when read together with the accompanying drawings, in which:
`
`20
`
`• Figure 1 is a :flowchart depicting a method for interruptible autonomous control of a
`
`vehicle in accordance with an embodiment o:f the invention;
`
`• Figure 2 is a block diagram depicting a systeITI for interruptible autonomous control
`
`of a vehicle in accordance with an embodiment of the invention;
`
`• Figure 3 is a flow chart depicting a method for processing a safety signal in an
`
`25
`
`autonomous vehicle in accordance with an elilbodiment of the invention;
`
`• Figure 4 is a block diagram depicting a systeITI for processing a safety signal in an
`
`autonomous vehicle in accordance with an e1Y1.bodiment of the invention;
`
`• Figure 5 is a :flowchart depicting a method for tracking a terrain feature by an
`
`autonomous vehicle in accordance with an elilbodiment of the invention;
`
`IPR2025-00943
`Tesla EX1025 Page 9
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`-9-
`
`• Figure 6 is a block diagram depicting a system for tracking a terrain feature by an
`
`autonomous vehicle in accordance with an em.bodiment of the invention;
`
`• Figure 7 is a flowchart depicting a method for the behavior based control of an
`
`autonomous vehicle in accordance with an e1nbodiment of the invention;
`
`5
`
`• Figure 8 is a block diagram depicting a system for the behavior based control of an
`
`autonomous vehicle in accordance with an em.bodiment of the invention;
`
`• Figure 9 is a flowchart depicting a method for multi-modal control of a vehicle in
`
`accordance with an embodiment of the invention; and
`
`• Figure 10 is a block diagram depicting a system for multi-modal control of a vehicle
`
`in accordance with an embodiment of the invention.
`
`Detailed Description
`
`[0033) As shown in the drawings for the purposes of illustration, the invention may be embodied
`
`in systems and methods for controlling vehicles, where the systems and methods compensate,
`
`with little or no operator intervention, for changes in the environment around the vehicle.
`
`15
`
`Embodiments of the invention enhance overall mission effectiveness and operating safety.
`
`[0034) In brief overview, Figure 1 is a flowchart depicting a method 100 for interruptible
`
`autonomous control of a vehicle in accordance with an embodiment of the invention. The
`
`method includes a step of first identifying one or more input devices in the vehicle (STEP 104).
`
`An input device may be an operator input device that directs at least part of the vehicle (e.g., one
`
`20
`
`or more ofa steering wheel, handle, brake pedal, accelerator, or throttle). The input device also
`
`may be a device directly or indirectly connecting the operator input device to a controlled
`
`element (i.e., the object in the autonomous vehicle ultimately controlled by the operator input
`
`device). For example, the operator input device can be a drive control. A drive control generally
`
`includes a throttle, brake, or accelerator, or any combination thereof. In other embodiments, the
`
`25
`
`operator input device can be an articulation control. An articulation control generally operates
`
`equipment attached to the vehicle. This can include, for example, a control used to manipulate a
`
`blade on a bulldozer, or a tilling apparatus on a tractor. Although a human operator typically
`
`accesses and manipulates the operator input device, the input device need not be accessible or
`
`operable by the human operator.
`
`IPR2025-00943
`Tesla EX1025 Page 10
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 10 -
`
`[0035] Next, the method 100 includes the step of providing one or more control policies (STEP
`
`I 06) corresponding to the input device. Generally, the control policies determine the manner in
`
`which the vehicle operates including, for example, whether the control of the vehicle will be
`
`autonomous, manual, or a combination thereof. In addition to the identification of the input
`
`5
`
`devices and control policies, the invention also includes the step of providing one or more
`
`actuators (STEP 108) associated with one or more input devices. The actuator is typically an
`
`electro-mechanical device that manipulates the input device. Manipulation occurs by, for
`
`example, pushing, pulling, or turning the input device, or by any combination thereof. A result
`
`of this is the autonomous control of the vehicle. Furthermore, in an embodiment of the
`
`10
`
`invention, the actuators still allow manual operation of the vehicle. In other words, the presence
`
`of actuators in the vehicle does not preclude manual operation of the corresponding input
`
`devices. In some embodiments, a linkage or other mechanical transmission associates the
`
`actuator with the corresponding input device. A linkage is generally apparatus that facilitates a
`
`connection or association between the input device and the actuator. A typical linkage is a lever
`
`15
`
`and pivot joint, a typical transmission is a rack and pinion device.
`
`[0036] Following the identification of the input device (STEP 104), providing the control policy
`
`(STEP 106), and providing the actuator (STEP 108), an embodiment of the invention provides
`
`autonomous control of a vehicle (STEP 102). Autonomous control allows a vehicle to be
`
`operated according to programmed instructions, with little or no operator intervention.
`
`20 Autonomous control typically includes "intelligence" that allows the vehicle to compensate for
`
`unforeseen events, such as an encounter with a terrain feature such as an obstacle. During
`
`autonomous control, an embodiment of the invention monitors the input devices and actuators
`
`for a disassociation therebetween (STEP 110). The disassociation is generally any break in a
`
`physical connection between the input device and the corresponding actuator. For example, the
`
`25
`
`input device can be an operator input device, such as an accelerator pedal, connected to an
`
`actuator that is a rack and pinion device. An operator can disassociate the accelerator from the
`
`actuator by, for example, depressing the accelerator. In some embodiments, the disassociation is
`
`detected by measuring the response of one or more sensors (STEP 112).
`
`[0037] On detection of the disassociation (STEP 110), autonomous control is interrupted in favor
`
`30
`
`of other operational modes (STEP 116). For example, on detection of the disassociation, a
`
`system according to an embodiment of the invention initiates a vehicle shutdown sequence
`
`IPR2025-00943
`Tesla EX1025 Page 11
`
`

`

`WO 2006/047297
`
`PCT/0S2005/037918
`
`- 11 -
`
`(STEP 114). This can occur when, for example, the vehicle operator depresses a "panic button,"
`
`thereby allowing a controlled, safe shutdown of the vehicle.
`
`[0038) In other embodiments, following detection of the disassociation (STEP 110), autonomous
`
`control is interrupted (STEP 116) to allow manual control (STEP 118). One example of this
`
`5
`
`occurs when an operator wants to increase temporarily 1:he speed of a vehicle that is under
`
`autonomous control. By depressing the accelerator, a system according to an embodiment of the
`
`invention relinquishes the autonomous control and allows the vehicle to accelerate according to
`
`the operator's preference.
`
`[0039] After the interruption of autonomous control (STEP 116), different embodiments of the
`
`10
`
`invention detect a restored association between the input device and the corresponding actuator
`
`(STEP 120). The reassociation is typically entails the reestablishment of the physical connection
`
`between the input device and the corresponding actuator. This is generally detected by
`
`measuring the response of one or more sensors (STEP 122). In the example discussed above, the
`
`reassociation would occur when the operator stops depressing the accelerator, thereby allowing
`
`15
`
`the accelerator to reconnect with its actuator.
`
`[0040) Following the reassociation, one embodiment of the invention establishes a revised
`
`vehicle control (STEP 124). The nature of the revised vehicle control depends on the control
`
`policy provided (STEP 106). For example, in some embodiments, the revised vehicle control
`
`includes returning to autonomous control (STEP 102). This can occur immediately. In other
`embodiments, returning to autonomous control (STEP 102) occurs after a delay (STEP 126). In
`
`20
`
`different embodiments, the operator must first intervene (STEP 130) before the vehicle returns to
`
`autonomous control (STEP 102). This configuration provides, for example, a s