Autonomous Decision Making Process TRIZ Cases

A parking controller determines optimal linear and turn paths for autonomous vehicles entering perpendicular spots.

Controller compares distance-based and completion-time parameters to discontinue autonomous control when merging safety requires human intervention.

A computer-aided driving system uses microphone arrays and neural networks to identify emergency audio signals in surrounding sounds.

Autonomous driving controller tracks neighboring vehicle movements to generate temporary routes when rule-based path planning fails due to obstacles.

A control apparatus estimates occupant emotions via multi-modal sensors and shares data between vehicles to notify drivers of nearby emotional states.

A dual model vehicle control system decouples rotation and translation parameters for precise trajectory prediction.

Passive infrared sensors detect human thermal signatures to trigger vehicle steering or braking actions.

An adaptive driving system adjusts vehicle routing and control parameters based on detected cargo characteristics.

A multi-channel safety architecture uses runtime invariant monitors to validate autonomy outputs and uphold safety requirements.

Recurrent neural networks predict surrounding vehicle trajectories using contextual constraints to resolve automation complexity trade-offs.

Circuitry detects energy conditions and geographic location to enter economy mode, resolving the trade-off between speed and consumption.

A neural network compares image data against a friction coefficient threshold to trigger targeted retraining using vehicle sensor inputs.

A processor classifies environmental objects using driver gaze data to build a priority-based decision database for autonomous vehicles.

A Dynamic Window Approach algorithm adjusts velocity vectors for automated lane changes.

Travel control system adjusts vehicle speed to maintain driving assist mode continuity during environmental changes.

A vehicle controller selects dynamic or hybrid kinematic models based on gear position to manage lateral and heading errors.

Controller predicts proximate vehicle behavior using a planning-based approach that optimizes cost functions from the second vehicle perspective.

A computing device assigns maneuver labels to autonomous vehicle sensor data using a weighted directed graph of candidate path plans.

An autonomous accessory support moves with patients to maintain preset distances between medical devices and the patient.

A travel control device adjusts vehicle limits based on speed to enable smoother lane changes and turns.

A steerable lighting device illuminates uncertain areas to enhance sensor data acquisition.

A travel control apparatus adjusts inter-vehicle distance thresholds based on driving automation levels to manage vehicle start timing.

A driving mode decision support system determines optimal manual or autonomous operation based on user profiles and road segment data.

Segmenting detected objects by driving parameters reduces computational load while maintaining predictive accuracy for atypical vehicles in dense traffic.

A laser scanner device uses a rotating mirror and polygon or MEMS for beam steering to achieve high-resolution scanning.

Networked buoy systems provide autonomous positioning and communication across vast ocean areas, resolving coverage gaps in remote monitoring environments.

A tow vehicle control system autonomously maneuvers along user-defined waypoints using rear camera imagery and wheel encoder data.

A left-side trigger pedal initiates autonomous driving without interfering with steering or braking inputs.

Aggregating pedestrian safety messages via DSRC enables motion profile selection that resolves adaptability complexity trade-offs.

A system detects user identity to select a target automatic driving mode from pre-stored options.

A vehicle control device selects lane markings for keeping by collating map-based lane shape data with peripheral image data.

Radar-guided UAV navigation captures validation images at detected movement locations, reducing false alarms from environmental reflections.

A mixed-mode vehicle control unit enables autonomous driving by verifying launch area location and user absence.