Autonomous Decision Making Process TRIZ Cases

A vehicle dynamic model serves as the main process model within a navigation filter to estimate position and velocity.

An information processing device derives expected arrival times to permit side trips in automatic driving vehicles.

A decision point engine generates vehicle trajectories by calculating stopping profiles based on detected object data.

A collision avoidance apparatus dynamically adjusts its sensing region size and shape to detect objects near automated guided vehicles.

A trajectory planning system fixes steering and speed parameters for different durations to compute input controls without parameter changes.

Autonomous rail vehicles adjust movement parameters dynamically using mobile app ride requests for flexible on-demand service.

A controller segments neural processor modes via a mechanical switch to resist subversion while maintaining operational integrity.

Dual lane side detectors spaced wider than the vehicle provide accurate lateral distance control, eliminating latency from wireless communication delays.

Segments touch panel drive controls from mechanical door and ramp switches to eliminate erroneous operations during vehicle entry.

A sensor cleaning system for autonomous vehicles executes user-selected plans to remove obstructions.

Deep neural networks analyze image data to determine vehicle orientation and lateral position for autonomous path navigation.

An autonomous guiding vehicle connects to self-propelled carts to provide navigation data and electrical energy.

Autonomous mobile objects patrol routes to detect speeding violations without roadside monitors, eliminating infrastructure complexity.

A multi-sensor system combines point cloud data with attribute information to identify actors in physical spaces.

Cloud architecture segments processing between vehicle and server, reducing resource strain while enabling OEM data sharing.

A vehicle control device adjusts lateral intervals based on surrounding traffic participants and road structures.

A vehicle control device manages host vehicle travel across autonomous, remote, and manual driving modes.

A multi-sensor object recognition apparatus calculates detection differences to decide result reliabilities.

Frequency domain conversion filters extraneous signals from neighboring regions, enabling precise vehicle positioning relative to target boundaries.

A vehicle control system communicates with a portable device to manage steering, propulsion, and brakes based on device presence.

Central server coordinates autonomous vehicle work area reservations through broadcast signals and conflict detection mechanisms.

An interactive autonomous vehicle agent generates experience tuples using separated quality and behavior models for reinforcement learning.

A service server merges sensor inputs from diverse autonomous vehicles via competitive computing to resolve algorithmic instability and ensure safe operation.

Inverse reinforcement learning adjusts path planning weights dynamically to resolve abrupt maneuver bottlenecks in autonomous driving.

An offroad travel assistance system evaluates vehicle configuration against reference trail data to prevent mechanical damage.

A vehicle platform control system shares sensor data and coordinates with external entities through modular communication interfaces.

A recurrent neural network integrates front and rear camera data to determine hazardous situations.

Integrates sensor readings and map data into machine learning models to improve prediction accuracy without increasing system complexity.

A vehicle control system transposes adjacent lane boundary indicators onto the current traffic lane to define virtual edges and centerlines for position maintenance.

Dynamic projection of intent icons conveys right-of-way confidence, resolving communication gaps at intersections.

Autonomous aerial devices navigate to spatial locations for self-configuration, reducing manual setup time and errors.

A controller calculates a steering override reference value using collected driving data to adjust control modes.

Redundant interface devices deliver vehicle commands to eliminate single-point failures in autonomous systems.

An autonomous vehicle operating apparatus dynamically switches between fully autonomous and driver-assisted traveling modes based on detected circumferential conditions.

A detecting vehicle identifies road hazards and transmits specific condition data to affected nearby vehicles.

A driving assistance device detects driver seat attitude changes to trigger timely steering wheel hold requests during automated mode transitions.

A vehicle running control apparatus adjusts target paths based on real-time deviations to enhance driving stability.

Ranking maneuver patterns by comfort scores reduces computational complexity while maintaining trajectory safety.

Perception system observes person behavior and contextual cues to determine traffic direction likelihood.

A vehicle control device adjusts speed and lateral position to clear blind areas before switching driving modes.

Merging multiple sensor streams into one 3D model resolves the trade-off between navigation accuracy and device complexity.

Logic device monitors control surface angles to generate release signals that disable the autopilot pump, resolving manual intervention delays.

Evaluates lane change danger using internal vehicle data to infer external threats, resolving sensor range limitations.

The iREAD system architecture fuses preview information with vehicle energy efficiency data to enable real-time eco-routing and powertrain control.

An autonomous parking apparatus uses LiDAR and ultrasonic sensors to generate local map data for detecting available spaces.

A vehicle control system collects subjective user evaluations alongside quantitative sensor data to adjust autonomous maneuver operations.