摘要:
A system for calculating a movement direction and position of a movable object such as an unmanned vehicle running within a factory and a method therefor are disclosed in which an image pick up camera such as a video camera photographs a background of the movable object to generate a background two-dimensional image. Positions of vanishing point and side ends of a passage on which the movable object is to move are derived from the background photographed two-dimensional image. The movement direction of the movable object is derived from the detected vanishing point. Distances of the movable object from both sides ends of the passage are derived on the basis of the detected vanishing point and positions of side ends of the passage. the movement direction and position of the movable object thus detected are used to control movement of the movable object. The vanishing point is detected on the basis of edge directions at all points constituting and edge on the background two-dimensional image.
摘要:
An image processing section receives data from cameras mounted on the vehicle and produces an image or images from which a first set of so called "local" data is derived and compiled. A sensor section senses the rotational characteristics of two vehicle wheels and the conditions prevailing on either side of the vehicle and complies a second set of so called "global" data. The local and global data are compared and data is only accepted in the event that the differences between the two sets of data fall within predetermined limits and data which falls outside of the ranges deemed erroneous and rejected.
摘要:
Stereo image data depicting the lane on which the vehicle is running is rectified into a planar image on which one or more level lines can be generated in a manner to intersect one or both of the edges of the lane. Angles are measured between lines which extend from these the points if intersection in directions normal to the level line or lines and lines which extend tangentially to any curvature which occurs in the road edges at the point of intersection. These angles are recorded, the difference therebetween determined and compared in a manner which determines the attitude of the vehicle on the road. The curvature of the road and the vehicle speed are determined and the best steering angle for the road wheels determined in accordance With a schedule which is recorded in terms of attitude and a parameter variable with the vehicle speed and road curvature.
摘要:
A speech recognition system for an automotive vehicle which can record or recognize spoken instruction phrases reliably even when engine noise increases high within the passenger compartment. When the engine begins to operate, the gain of an amplifier of a speech input section or the threshold level of a voice detector is so switched as to reduce the sensitivity to spoken instructions. As a result, the driver must necessarily utter a spoken instruction in a louder voice and thus the proportion of noise level to spoken instruction signal level is reduced. The system according to the present invention comprises engine operation detecting means, an analog switch, two amplifiers or two multipliers, etc. in addition to the conventional speech recognizer.
摘要:
A speech recognition and actuator system for auto device control includes a recognition switch which when operated a first time activates the system to accept a spoken command, and if operated a second time within a predetermined interval T1 (approximately 2 seconds) stops the actuation and awaits a new command. Additional timers provide interval T2 for a stop command, and T3 for enabling the speech recognizer. The system may also include a reset switch when operated returns the actuated device to its original state.
摘要:
A spoken-instruction controlled system for an automotive vehicle by which a single actuator can be activated repeatedly or a plurality of actuators can be activated sequentially by repeatedly depressing a recognition switch within a predetermined time period after a spoken instruction corresponding to the single actuator or actuators has been recognized by a speech recognizer. Therefore, it is possible to activate an actuator repeatedly or actuators sequentially without uttering the same spoken instruction repeatedly. The spoken-instruction controlled system according to the present invention comprises a two-circuit analog switch, at least one analog switch, at least one retriggerable timer unit, an AND gate, an OR gate, a shift register, etc., in addition to a speech recognizer.
摘要:
A speech recognition system for an automotive vehicle which can selectively activate actuators according to vehicle-travelling conditions in such a way that a spoken instruction such as "Door open" or "Trunk lid open" can be recognized only when vehicle speed is zero, "Headlight high/low beam" can be recognized only when vehicle speed reaches a predetermined value, and "Air conditioner on/off" or "Radio on/off" can be recognized regardless of vehicle speed. The speech recognition system for an automotive vehicle according to the present invention comprises a speed sensor or the like and a speed-dependent speech selection unit including AND gates or analog switches, in addition to the conventional speech recognizer.
摘要:
A speech recognition system for an automotive vehicle enables desired reference spoken instruction phrases to be easily re-recorded by repeatedly depressing a manual switch arrangement that commands skipping. Each activation of the switch shifts the system from a ready state for recording the current spoken instruction to a ready state for recording a succeeding spoken instruction. By repeatedly activating the skip switch ready state for re-recording any given spoken instruction is reached. In one embodiment, a separate skip switch is provided. In a second embodiment, logic circuitry responds to simultaneous activation of record and recognition switches to command skipping.
摘要:
In a speech recognition and control system for an automobile, the microphone preamplifier gain is made inversely proportional to the background sound noise level. Noise level is determined by averaging the microphone output for 100 milliseconds after the recognition switch is closed, before speech.
摘要:
A speech recognition system includes speech presence detection which uses a first level threshold of ambient noise/silence above which speech start is decided for a signal. Speech end is decided when the signal falls to a second threshold equal to the first, unless a predetermined time interval of speech is exceeded after start, causing a corrected second threshold to be calculated and used.