Autonomous Decision Making Process TRIZ Cases

A vehicle control device selects notification timing for driving takeover requests based on travel speed to optimize the transition from automated to manual operation.

Autonomous vehicle system coordinates driverless fuel replenishment to resolve refueling time delays and station availability constraints.

Segmenting control into distinct operation modes resolves the complexity of multi-user access while maintaining safety thresholds.

An autonomous vehicle mode regulator system receives wireless authorization signals from roadway infrastructure to control operational automation levels.

A pruning robot system uses RFID tags and GPS for precise navigation and automatic pruning operations in plantations.

A physical stop switch disconnects power from a software-operated vehicle section, preventing cyberattack takeover without software intervention.

A computing device assesses environmental predictability to activate interactive model predictive control for autonomous vehicle actuation.

Forecast Assured Navigation predicts GNSS signal availability using 3D maps and satellite data.

An automatic driving system generates a traveling plan to moderate vehicle behavior changes during engagement startup.

Dynamic wavelength switching filters return pulses against emitted light, reducing pixel errors from concurrent beam scanning.

A multi-model redundancy system verifies autonomous driving actions using specialized neural networks for safety, legality, and ethics checks.

Autonomous vehicle navigates to a biased edge position before changing lanes, resolving dense traffic space constraints.

A 1:5 scale RC truck platform with integrated sensing and control units bridges simulation gaps while reducing safety risks.

Autonomous drones replace manual surveying by deploying markers and collecting GNSS data, eliminating labor risks in hazardous locations.

A probabilistic graph model predicts merging vehicle intentions using velocity history and time-to-merge data for autonomous driving control.

Cloud intermediaries aggregate vehicle sensor data to construct collaborative predictive threat vectors, enabling proactive risk mitigation across the fleet.

A behavior prediction device estimates deviation reasons to determine model update necessity.

A processor determines a size adjustment factor to predict the laterally innermost point of forward objects using sensor data.

A control unit coordinates multiple motor vehicle safety functions by recognizing a primary trigger signal and generating secondary signals for different function types.

Segmenting power supplies into redundant units prevents single-point failures, ensuring continuous vehicle control when primary sources degrade.

An authorization device checks occupant criteria before enabling semi-autonomous driving mode.

A cloud computing control system determines optimal speed trajectories and neutral coasting commands for vehicle platoons.

Navigation system guides autonomous vehicles along defined paths using plant row markers, detecting towed implement malfunctions to prevent equipment damage.

Fuzzy controller generates linear models mapping state-action values to sensor data for interpretable autonomous driving control.

A vehicle control system predicts surrounding cut-in maneuvers using sensor data features to enable proactive speed adjustments.

A work machine control system uses a non-contact sensor to detect object positions around the vehicle.

Classifying wheel orientation via neural networks resolves the trade-off between prediction accuracy and processing time for stopped vehicles.

A platoon coordination vehicle resolves coupling conflicts to optimize fuel consumption for autonomous vehicle groups.

A digital environment model generates virtual objects for automated vehicle testing.

A vehicular information presenting device conveys attention-arousing signals to the driver during autonomous drive transitions.

Multi-layer trajectory initialization corrects state estimation errors via feedback, preventing abrupt acceleration and ensuring ride comfort.

A motor vehicle control system assesses accident risk across function components to select the safest operational path.

Segmenting general models into individual profiles improves prediction accuracy while reducing device complexity.

An autonomous dock system calculates vehicle speed and clutch torque to maintain precise positioning during the docking maneuver.

A shared-use vehicle system automatically adjusts seat positions and camera angles using onboard computers and stored user preferences.

Replacing physical guidance lines with coordinate-based virtual paths eliminates expensive hardware modifications while enabling real-time speed control.

A mission planning system divides job sites into sub-regions, paths, and layers to assign tasks to autonomous work vehicles.

System maintains operator alertness via periodic mode transitions to resolve detection confidence issues in autonomous vehicles.

Three lidar sensors on a cab roof provide 360-degree coverage around an autonomous articulated soil compactor.

Zone-specific decision logic resolves safety and efficiency trade-offs in unprotected left turns.

A LiDAR processing system decomposes range measurements into height and ground projections to identify ground points.

A decentralized blockchain database collects distributed driving data to generate real-time risk assessments for autonomous vehicles.

Parallel illumination from a VCSEL array increases point cloud density while reducing device complexity compared to sequential scanning systems.

Processor associates traffic lanes with control devices using sensor data, eliminating manual annotation costs and time.

Segmenting the parking robot into wheel-mounted units allows overcoming ramps while maintaining high travel speeds in multistory car parks.

Autonomous vehicle computing system classifies zones and calculates entry times to resolve traffic congestion during passenger service.

Dynamic steering counterforce reduces resistance when returning to the lane center, balancing automated stability with manual intervention ease.

An autonomous vehicle system selects parking areas by comparing expected idle time against location thresholds.