Abstract: A movable game controller for controlling aspects of a computer controlled game display with apparatus for determining the linear and angular motion of that movable controller. The apparatus includes a plurality of self-contained inertial sensors for sensing the tri-axial linear and tri-axial angular motion of the moving controller. Each sensor is mounted at a fixed linear position and orientation with respect to the others. The linear and angular motion of the controller is computed from the correlated motion sensor readings of each of the plurality of self-contained inertial sensors.

Abstract: Techniques for performing accurate and automatic head pose estimation are disclosed. According to one aspect of the techniques, head pose estimation is integrated with a scale-invariant head tracking method along with facial features detected from a located head in images. Thus the head pose estimation works efficiently even when there are large translational movements resulting from the head motion. Various computation techniques are used to optimize the process of estimation so that the head pose estimation can be applied to control one or more objects in a virtual environment and virtual character gaze control.

Abstract: A video gaming system includes a wireless controller that senses linear and angular acceleration to calculate paths of controller movement over a broad range of controller motion. The system also includes an electromagnetic alignment element, such as a set of LEDS. The controller includes an additional sensor to sense light from the LEDs over a relatively restricted range of controller motion, and use this sensed light to dynamically calibrate the controller when the controller passes through the restricted range of motion over which the sensor senses the light.

Abstract: Techniques for interpreting orientation invariant motion are disclosed. Unlike a prior art controller that has a specific physical design to induce or force a user to grip the controller in a consistent way, a disclosed controller does not have such a physical design and allows a user to grip the controller in any way that is comfortable to the user. One or more transformations or rotations are designed to transform or rotate readings from inertial sensors housed in the controller to readings independent from how the controller is being gripped by a user.

Abstract: Techniques for controlling movements of an object in a videogame are disclosed. At least one video camera is used at a location where at least a player plays the videogame, the video camera captures various movements of the player. A designated device (e.g., a game console or computer) is configured to the video data to derive the movements of the player from the video data, and cause the object to respond to the movements of the player. When the designated device receives video data from more than one locations, players at the respective locations can play a networked videogame that may be built upon a shared space representing some or all of the real-world spaces of the locations. The video game is embedded with objects, some of which respond to the movements of the players and interact with other objects in accordance with rules of the video games.

Abstract: Techniques for selecting a portion of a 3D virtual environment are disclosed, where the portion of the 3D virtual environment may be one or more objects in the 3D virtual environment or one of scenes in the 3D virtual environment. A motion sensitive device (controller) is used. The controller generates sensor data sufficient to derive position and orientation of the controller in six degrees of freedom. In one embodiment, when selecting the portion of the 3D virtual environment, the controller generates a ray to an interaction of a display screen provided to display the 3D virtual environment, wherein the ray is further projected into the 3D virtual environment by a ray tracing technique as if the user had a real laser pointer that crosses from the physical world into the 3D virtual environment being displayed. Further a user is optionally to use a secondary input device to select one or more points or objects in a 3D space to control a distance along the ray being used.

Abstract: A movable game controller for controlling aspects of a computer controlled game display with apparatus for determining the linear and angular motion of that movable controller. The apparatus includes a plurality of self-contained inertial sensors for sensing the tri-axial linear and tri-axial angular motion of the moving controller. Each sensor is mounted at a fixed linear position and orientation with respect to the others. The linear and angular motion of the controller is computed from the correlated motion sensor readings of each of the plurality of self-contained inertial sensors.

Abstract: Techniques for supporting generalized motion recognition are disclosed. A set of motion recognizers created from training sets of labeled processed motion signals is provided, each of the component outputs is transformed. When a motion signal including two or more component outputs is received, the component outputs are transformed into device-independent motion signals, where each of the component outputs describes a different component of a motion made by a user. The motion recognizers are applied to the motion signal to build generalized motion recognizers responsive to the motion sensitive device that has generated the motion signal.

Abstract: Techniques for performing anytime motion recognition are disclosed. Based on a motion signal received from a motion-sensitive device being manipulated by a user as a way to interact with an application, a processing unit is configured to a set of prototypes included in a motion recognizer to generate a recognition signal from the motion signal in response to the motion recognizer. A prototype is eliminated out of the set of the prototypes from further consideration when a corresponding running distance of the prototype to the motion signal is beyond a predefined measurement so that the motion recognition speeds up as time passes.

Abstract: Techniques for performing motion recognition using generalized motion recognition capability are disclosed. At least two types of sensors are used to generate sensor signals about a motion made by a user. The sensor signals are then transformed to device-independent motion signals that may be used to build generalized motion recognizers or used with one or more generalized motion recognizers responsive to the sensors. At least one of objects in a virtual interactive environment is responsive to a recognition signal determined from the motion signal and the generalized motion recognizers.

Abstract: Techniques for tuning motion recognizers in motion detections are described. The motion recognizers are created or generated in advance by trained users. The motion recognizers are then loaded into a processing unit that receives motion signals from a handheld motion sensitive device being controlled by an end user. While motion recognition of the motion signals is being made, some or all of the motion recognizers are tuned by the motion signals to make the motion recognizers more adaptive to the user.

Abstract: Techniques for motion recognition using multiple data streams are disclosed. Multiple data streams from inertia sensors as well as non-inertial sensors are received to derive a motion recognition signal from motion recognizers. These motion recognizers are originally constructed from a training set of motion signals and may be updated with received multiple sensing signals. In one aspect, multiple data streams are converted to device-independent motion signals that are applied with the motion recognizers to provide a generalized motion recognition capability.

Abstract: Techniques for non-disruptive embedding of specialized elements are disclosed. In one aspect of the techniques, ontology is defined to specify an application domain. A program interface (API) is also provided for creating raw features by a developer. Thus a module is provided for at least one form of statistical analysis within the ontology. The module is configured automatically in a computing device with the API in response to a system consistent with the ontology, wherein the system has no substantial requirement for specialized knowledge of that form of statistical analysis, and the module has no substantial requirement for specialized knowledge of particular functions provided by the system.

Abstract: Methods and systems capable of determining which subset of a set of logical expressions are true with relatively few evaluations of the primitives that together with any standard logical connectives, make up the logical expressions. A plurality of directed acyclic graphs, each graph including at least one root node, at least one leaf node, and at least one non-leaf node associated with a leaf node. Each node is associated with a, possibly empty, subset of presumed to be true logical expressions. Each non-leaf node is associated with one of the primitives mentioned in any of the logical expressions. Edges are defined between two of the nodes, each edge being associated with a possible value, or range of possible values, of the primitive associated with the node at the tail of the edge. Paths are defined through each of the directed acyclic graphs from a root node to a leaf node by recursively following each edge corresponding to the current value of the primitive at a selected non-leaf node.

Abstract: Techniques for using motion recognizers are described. The motion recognizers are created or generated in advance by trained users. The motion recognizers are then loaded into a processing unit that receives motion signals from one or more motion sensitive devices being manipulated by one or more end users to control one or more objects in a virtual environment. Depending on implementation, the virtual environment may represent a remote scene or a video game, where objects in the virtual environment can be controlled by the users to perform desired actions or moves.

Abstract: Methods and systems capable of creating a component for determining which subset of a set of logical expressions are true with relatively few evaluations of the primitives that, together with any standard logical connectives, make up the logical expressions.

Abstract: A movable game controller for controlling aspects of a computer controlled game display with apparatus for determining the linear and angular motion of that movable controller. The apparatus includes a plurality of self-contained inertial sensors for sensing the tri-axial linear and tri-axial angular motion of the moving controller. Each sensor is mounted at a fixed linear position and orientation with respect to the others. The linear and angular motion of the controller is computed from the correlated motion sensor readings of each of the plurality of self-contained inertial sensors.

Abstract: Generating motion recognizers from example motions, without substantial programming, without limitation to any fixed set of well-known gestures, and without limitation to motions that occur substantially in a plane, or are substantially predefined in scope. From example motions for each class of motion to be recognized, a system automatically generates motion recognizers using machine learning techniques. Those motion recognizers can be incorporated into an end-user application, with the effect that when a user of the application supplies a motion, those motion recognizers will recognize the motion as an example of one of the known classes of motion. Motion recognizers can be incorporated into an end-user application; tuned to improve recognition rates for subsequent motions to allow end-users to add new example motions.

Abstract: Providing dynamic learning for software agents in a simulation is described. The software agents with learners are capable of learning from examples. When a non-player character queries the learner, it can provide a next action similar to a player character. A game designer provides program code, from which compile-time steps determine a set of raw features. The code may identify a function (like computing distances). At compile-time steps, determining these raw features in response to a scripting language, so the designer can specify which code should be referenced. A set of derived features, responsive to the raw features, may be relatively simple, more complex, or determined in response to a learner. The set of such raw and derived features form a context for a learner. Learners might be responsive to (more basic) learners, to results of state machines, to calculated derived features, or to raw features. The learner includes a machine learning technique.