External Condition Input Parameters TRIZ Cases

Staged U-turn guidance informs passengers of maneuver type and timing, reducing anxiety while supporting reliable autonomous turning.

Rule-based gap checks rank lane-change options and stop weak candidates early, improving score interpretability and saving compute.

Adaptive switching between acceleration and deceleration devices improves autonomous vehicle speed control accuracy while reducing ride discomfort.

By modeling driver-specific risk from straight-driving data, this case improves lane change prediction for smoother and safer host vehicle control.

When ML driving models face unfamiliar road conditions, a remote control link lets a human operator take over steering, braking, or acceleration.

Front-vehicle sensing and display guidance help rear vehicles judge safe overtaking points on narrow roads with limited visibility.

Relative distance mode analysis separates driver behavior from traffic effects, improving driving risk diagnosis from inter-vehicle spacing.

Multiple path estimates are fused with reliability checks and defect detection to keep vehicle control stable when sensors degrade or conditions change.

When a vehicle cannot complete a task, a server identifies installed inactive features and activates the right one to restore mobility and safety.

Partitions a lane widening zone into two sub-zones so lateral guidance can switch reference paths safely when lane markings are unclear.

Lateral-acceleration gating stops ACC re-acceleration only when a lead vehicle is lost in a curve, reducing collision risk without needless speed limits.

Dynamic candidate future intents help predict agent trajectories more accurately by adapting to scene changes without collapsing diverse action paths.

A modular autonomy and vehicle dynamics split maps target acceleration to wheel torque, reducing vehicle-specific calibration across EV platforms.

Work-zone geometry is used to segment lanes, score safe paths, and adjust lane departure tolerance for more reliable lateral assist.

Using upcoming turn data from navigation or map sources, this case triggers braking early to keep wheel-road contact in tight corners.

Camera and inertial event scoring groups drivers by coachable risk and sends alerts only when behavior changes can shift category.

When the main controller fails, an auxiliary controller monitors its state and takes over vehicle control to avoid uncontrollable driving situations.

Warning priority is raised when monocular camera distance estimates conflict with sensor data and image-motion features indicate a moving hazard.

Temporal buffers on predicted object trajectories help autonomous vehicles cross intersections more safely and comfortably than spatial-only planning.

When vehicles or pedestrians interrupt convoy travel, the controller keeps tracking the lead vehicle and rebuilds a safe restart trajectory.

Scene-aware speech embeddings turn natural language into vehicle control signals, improving command accuracy for autonomous driving.

Adaptive cruise control adjusts motorcycle speed from longitudinal and lateral spacing, using vehicle-type lateral limits for safer overtaking.

Alerts are triggered only when a nearby vehicle enters the assist area from the front, reducing false warnings when passing trucks or buses.

Radar-based lateral distance detection lets a single-track vehicle identify group rides and avoid unnecessary overtaking during adaptive cruise control.