External Condition Input Parameters TRIZ Cases

Predicts path intersection zones and adjusts deceleration or trajectory using stopping-distance cost values to avoid cut-ins and near-collisions.

Calculating limit paths and feasible trajectories lets autonomous vehicles assess lane-change risk dynamically with lower computing load.

When rear sensing is limited, the vehicle starts near the shoulder, waits only when needed, and then shifts toward lane center to avoid sudden braking.

By comparing adjacent-lane vehicle density with relation-based thresholds, this case shows how autonomous lane changes can disperse traffic flow.

ANN and rule-based accessibility scoring adapts vehicle HMI and control content to occupant needs, reducing distraction during emergencies.

Adaptive steering override thresholds vary by assist mode, lateral threat, and vehicle dynamics to keep driver intervention natural and safe.

Predicted object trajectories add speed constraints so autonomous vehicles can handle intersections safely with smoother deceleration and less passenger discomfort.

Gain tuning based on cargo type coordinates longitudinal and lateral motion in vehicle platoons to improve comfort and maintain safe clearances on curves.

Variable jerk control adjusts automatic braking to cut collision risk while suppressing vehicle instability and ride discomfort.

Infrastructure-constrained prediction of tram movement helps automated vehicles generate steering and speed control signals to avoid urban collisions.

Continuous sensor feedback lets the processor reassess speed, distance, and nearby vehicles to continue or suspend an overtake safely.

Stored route data from other vehicles is checked against current sensing to keep lateral control reliable when onboard sensors degrade.

Multistage trajectory and scenario-tree planning helps autonomous vehicles anticipate other objects' reactions and avoid overly conservative navigation.

Sensor fusion detects abnormal driving and shifts vehicle control to a remote operator, improving safety when the driver or vehicle state is unstable.

Driving-signal intent detection shifts safety activation between first and second conditions to protect autonomous travel plans without losing hazard response.

By tracking two preceding vehicles, this control approach predicts traffic-jam restarts to avoid late acceleration, jerky motion, and unsafe gaps.

Predictive safety-zone evaluation and reinforcement learning help adaptive cruise control avoid rear-end collisions in uncertain traffic and road conditions.

Wheel-speed-based rough-surface detection filters throttle torque requests to reduce driveline oscillation and improve vehicle comfort.

Distinct double-tap or double-toggle consent helps autonomous vehicles avoid unintended lane changes while verifying safe maneuver timing.

Upper-bound SL cost terms let autonomous vehicle planners optimize SL, ST, and LT together to curb oscillation and lateral acceleration.

Restricting drive output within the current gear ratio keeps platoon vehicles responding uniformly and suppresses distance and speed variation.

Reference echo comparison lets ultrasonic sensing detect road friction changes and objects in real time for more reliable movable body control.

Real-time airflow sensing reveals hidden passages and terrain beyond line of sight, helping autonomous vehicles navigate disaster zones more safely.

Feedback correction compares actual and model acceleration to compensate vehicle model mismatch and keep speed control closer to target.

Sensor challenges and response analysis gauge driver readiness in real time for safer transitions between autonomous and manual control.

Environment and map data identify marked road stretches so cruise control can apply stored driver-preferred speeds for safer, smoother travel.

Biometric sensing and AI predict motion sickness in infants and sleepers, enabling route, rest, seat, and vehicle-state adjustments.

Earlier traffic-image display when autonomous deceleration is invalid gives drivers more time to respond to upcoming slowing needs.

Vehicle motion and wheel position response are used to estimate ground load-bearing capability across changing surfaces and conditions.

Different brake release rates after obstacle avoidance or driver input smooth the handoff from automated steering and braking.

Cell-based snow movement simulation guides autonomous plowing routes to improve coverage while reducing time, fuel, and vehicle wear.

Continuous driver skill evaluation gates automatic mode switching, reducing unsafe handover risk and improving transition reliability.

A user terminal tracks vehicle position by camera and stops follow-me motion when user supervision is interrupted.

Collision-free behavior sets and model trust checks help autonomous vehicles keep human-like driving without executing unsafe predictions.

Real-time road shape recognition enables early speed planning for mapless moving objects, helping avoid sudden deceleration at intersections.

A two-phase control strategy lowers speed before roundabout entry, then returns to a curvature-based target for smoother vehicle handling.

When sensor abnormalities trigger an emergency stop, this case plans a stop outside intersections to avoid blocking traffic and reduce collision risk.

Roadside beacons transmit bend geometry and turn conditions so vehicles can regulate speed through curves even where navigation data is unavailable.

Partitions a lane widening zone into subareas and switches reference paths to keep automated lateral positioning accurate through lane splits.

Image-based driver action recognition confirms intent to proceed at uncertain crosswalks, reducing unnecessary stops while maintaining safety.

Function modules with validity attributes let automated driving switch configurations by surroundings, improving flexibility across regions.

Maps safeguarded and safety-relevant regions around a vehicle to detect perception gaps and generate driving or infrastructure suggestions.

Constrained diffusion sampling guides multi-agent trajectory prediction to stay realistic, physically valid, and efficient for real-time navigation.

Sensor fusion tracks occupant emotion and driving deviations to recommend autonomous mode when abnormal behavior suggests distraction or distress.

A surrogate model maps road-scene features to sensor response statistics, cutting AV simulation test time while preserving evaluation fidelity.

Combining weather, ground, and wheel grip data enables faster, more reliable road surface detection for braking and torque adjustment.

Trajectory-based consolidation filters unstable and off-path detections to cut false braking in autonomous driving.

Real-time torque adjustment identifies the vehicle limiting platoon speed, improving uphill and acceleration performance while reducing fuel use.

Adaptive merge guidance varies tone, volume, and interval to signal acceleration or deceleration needs and ease driver speed alignment.

Risk-based emergency path selection lets autonomous vehicles keep control during module communication failures using speed and mass.