External Condition Input Parameters TRIZ Cases

Monitors controller and communication abnormalities, then reallocates autonomous or manual control rights to keep vehicle operation reliable.

Sensors and controller-guided driving missions train novice drivers in pedal, distance, and lane change skills while intervening to prevent accidents.

Adaptive haptic feedback lets a single vehicle control knob handle multiple functions by responding to user actions and driving conditions.

Urgency-based driver requests switch from sequential prompts to a direct urgent handover when automated driving needs a faster manual takeover.

Stored speed-limit offsets are automatically restored after temporary limit changes, reducing manual reset steps in adaptive cruise control.

V2X merge requests, approvals, and ETA checks let autonomous vehicles coordinate lane merges and avoid collisions with timely speed control.

Road-line and nearby-vehicle position analysis improves cut-in detection accuracy, enabling faster braking response and lower collision risk.

By analyzing where non-ego vehicle tracks leave the roadway, the control system detects road closures early enough to adjust trajectory.

Map- and sensor-based MRM control selects legal, lower-risk stopping positions by recognizing road structures, static objects, and weather.

Natural-language vehicle rules are generated from sensor and user data, then validated before execution to balance adaptability and robustness.

Repeated driver speed corrections trigger a proactive offset suggestion, helping speed control follow limits without obstructing traffic.

When a parked vehicle needs to communicate outside, window-displayed messages prioritize urgent alerts and support remote user approval.

When a stopped lead vehicle is likely to move at a green light, slower deceleration avoids abrupt control and better matches driver expectation.

A travel-envelope and four-corner object model simplifies real-time collision time prediction while preserving precision in driver assistance.

Integrated drive, braking, and active suspension compensation manages coupled yaw and roll motions to improve vehicle posture control.

Weight-based axle change detection lets vehicle controls adapt brake parameters after axle additions or removals, improving safety and operability.

Object detection quality is used to weight trajectory costs and braking limits, reducing unnecessary braking while preserving safe path selection.

A processor selects safe stop locations and adjusts deceleration to avoid crossings, intersections, and entrances during autonomous driving failures.

Upcoming braking, turning, and acceleration alerts on mobile or cabin outputs help passengers prepare for maneuvers and reduce motion sickness.

Sensor results are shown when detection quality drops or risk rises, helping monitor ML-based vehicle control reliability.

Kalman filtering fuses wheel rotation and GNSS positions to correct tire circumference drift and improve low-speed vehicle distance accuracy.

Acceleration profiles tied to accelerator pedal position make vehicle approach control feel more natural while adapting braking to hazards.

Pontryagin-based trajectory calculation cuts computation time and memory while preserving near-optimal vehicle energy savings in real time.

Adjacent-lane traffic evaluation lets automated longitudinal control cut relative speed and adjust spacing to lower multi-lane accident risk.

A neural network converts radar tensors into heatmaps to recover valid hits and build more accurate point clouds for AV object detection.

Relative lateral and longitudinal motion in road-aligned frames improves collision detection on curves and adjacent lanes while reducing false alarms.

Real-time traffic flow phases and travel change distance help autonomous vehicles cut intersection lane changes and improve ride stability.

Suppresses unnecessary PCS braking by verifying diagonal forward moving objects against nearby objects to filter false radar detections.

Sensor confidence intervals trigger speed, spacing, and traction-related behavior changes so autonomous vehicles stay stable on icy or snowy roads.

Sensors detect when an ego vehicle blocks another vehicle's expected maneuver, enabling prompt repositioning to cut delays and collision risk.

Eye gaze and scene analysis prioritize critical driving alerts, reducing warning overload while improving driver situational awareness.

Dynamic weighting of radar and IMU estimates improves vehicle motion accuracy under changing speed and weather conditions.

When a wall hides vehicles in a merging lane, speed is adjusted early using diagonal vehicle motion to avoid abrupt braking and driver anxiety.

Return-lane probability lets longitudinal guidance switch or retain the lead vehicle after an aborted lane change while maintaining safe spacing.

By limiting sensing to the calculated passing region, movable apparatuses avoid false obstacle alarms and reduce unnecessary avoidance delays.

Hybrid reinforcement learning and neural models infer individual vehicle driving coefficients in real time, improving prediction beyond cluster-level behavior.

Adaptive thresholds use nearby targets and driver gaze to separate collision avoidance maneuvers from true vehicle staggering.

By comparing current tire-contact data with ahead-of-vehicle sensing, the controller sets driving force limits more accurately and helps prevent wheel slip.

Historical traffic data and user preferences guide dynamic AD mode changes to align trip time, comfort, and energy use.

Existing vehicle sensors cap departure acceleration and speed to limit collision damage even when obstacles are missed at standstill.

Dynamic lateral checks compare steering demands with safety criteria and trigger braking before autonomous vehicles leave the route.

An AV handles occupant stop requests by pre-evaluating target locations and continuously replanning trajectories as road conditions change.

Preset driving parameter groups replace real-time modeling delays, adapting to driver preference and environment risk with faster control response.

Obstacle and accelerator sensing limit driving force, then apply staged braking to prevent pedal misapplication collisions with less shock.

Real-time target stop selection lets an autonomous vehicle handle speed-reducing requests safely by updating trajectory plans from map, traffic, and sensor data.

Predictive lane-change detection widens sensing during slipping-through travel to warn riders earlier while limiting false alerts.

Faulty lateral dynamics requests are checked against safety criteria before steering, with braking triggered to prevent route deviation.

Road obstacle sensing lets active suspension adjust ride height and damping so the vehicle can pass over obstacles with better safety and comfort.

Risk-based drivable area planning helps vehicles avoid obstacles smoothly, lowering collision risk without unnecessary stopping or lane changes.

Sensor data and guidance commands are assessed for driving risk, then unsafe commands are modified to help avoid collisions and losses.