Autonomous Decision Making Process TRIZ Cases

Radar detects lane markers via electromagnetic signatures, maintaining reliability through precipitation and wear.

Sensors on an autonomous cab-less yard truck enable precise trailer positioning while preventing collisions in dense storage areas.

A vehicle state determination device assesses sidewalk and roadway conditions to manage entry operations.

Merging onboard sensor data with V2X communications overcomes blocked views and improves path planning reliability.

Proximity sensors detect foot movements to switch vehicle control modes between autonomous and manual driving.

Automated image analysis replaces manual surveys by identifying and storing landmark attributes for accurate robotic localization.

Automatic driving controller maintains a new lane after occupant-initiated changes until specific conditions are met.

A drive planning device determines actions for events in a time-series manner to plan driving operations.

A vehicle environmental sensing evaluation system compares wireless reports from multiple cars to assess individual sensor reliability.

Classifier identifies sound types and cross-verifies with sensor data to detect hazards before visual occlusion limits perception.

A vehicle control system predicts trajectory paths and compares bumper elevations with roadway data to prevent scrapes.

A driving-rule system modifies automated vehicle parameters by detecting deviations in surrounding traffic behavior.

Neural network activation bypass skips zero-value multiplications while weight pruning removes redundant synapses to optimize processing resources.

A controller calculates virtual speed and steering angle from pedal displacement to enable safe manual driving mode transitions.

ECU compares GPS location with orientation data to reduce torque, preventing collisions from wrong-way vehicle entry.

Comparison module analyzes operator inputs against autonomous signals using threshold matching to enable safe manual takeover.

Offset path planning enables fast implement alignment while preventing jack-knifing and maintaining tractor stability.

Timestamped multiplexing aligns multi-source sensor data, resolving timing contradictions in autonomous vehicle fault simulation.

A UAV control system determines operating rules using sensor data to manage flight parameters.

A social driving style learning framework enables autonomous vehicles to perceive and adopt local driving behaviors through centralized data aggregation.

A driver observation device monitors attentiveness to trigger autonomous vehicle control.

An illumination controller changes LED patterns by waiting time to resolve insufficient visual communication at merging points.

A method registers vehicle trajectories and traffic light states to automatically allocate lanes to signals without directional road markings.

Control device determines sensor performance using positional data to detect degradation without adding complexity.

A blocking monitor system predicts spatial-temporal convergence to optimize vehicle routes.

A learning device performs deep learning of vehicle behavior patterns to predict and control speed or steering values based on the driving environment.

A machine-learning model calculates a yield score from sensor data to guide autonomous vehicle lane changes.

A vehicle control system manages driving support modes and equipment restrictions.

A sensor-equipped transport vehicle adjusts its permissible speed to prevent contact with identified objects in mixed traffic environments.

A vehicle park-assist controller uses acceleration data to enable or suppress parking spot identification.

A vehicle control system identifies destination types to manage autonomous parking and lane positioning.

A control device checks sensors and actuators before automatic travel begins.

A direct memory access mechanism transfers data between storage devices and graphics processing unit memory without CPU intervention.

A vehicle brake system controls driving torque and holding force using rotational speed sensor signal pulses to track wheel position accurately.

A joint classifier system processes stereo camera and optical flow sensor data to identify and classify unknown objects in autonomous vehicle environments.

Calibration tables select control commands matching current road conditions to maintain expected acceleration across varying environments.

A warehouse administration system determines side orientation for an industrial truck and transmits control commands to automatically align the vehicle.

A moving object controlling device determines control contents based on malfunction levels and peripheral situations.

Optimization server adjusts ADAS parameters based on refractometry data to maintain vehicle performance.

A time source recovery system synchronizes local and GPS clocks using smooth convergence to timestamp sensor data accurately.

A switching unit selects between triggered and automatic engagement modes to resolve driver authority versus operational complexity contradictions.

Ground-mounted pattern illuminating units project vehicle behavior data onto the road surface to convey motion state without generating acoustic noise.

A UAV system uses supervisory control to enable precise target location selection and autonomous navigation.

A vehicle control unit processes driving map data with deep neural networks to generate operational signals.

A control system detects the course of the own lane and identifies lanes occupied by following vehicles using environmental sensors.

A segmented vehicle control architecture routes requests through a remote computing environment for authentication before execution.

A UAV control system estimates heading using GNSS speed vectors during magnetic interference.

Station-lateral coordinate optimization minimizes lateral jerk for autonomous vehicle path generation.

A neural network determines mobile device location by processing signal data, eliminating simultaneous equation solving.

Segmenting path and velocity planning reduces search dimensionality, enhancing exploration rates for autonomous vehicles.