Autonomous Decision Making Process TRIZ Cases

An autonomous vehicle positions itself relative to obstacles to improve sensor visibility of a traffic lane.

A vehicle controller generates steering recommendations using terrain sensors to guide wheels over obstacles.

Hybrid time-of-flight and ultrasound sensing resolves detection range limits and ambient light interference for reliable obstacle avoidance.

A vehicle LAN switch selectively transmits sensor data streams based on the current driving mode to optimize network bandwidth usage.

An autonomous vehicle adjusts its position along a navigation route to optimize the view seen by an occupant.

A vehicle track prediction method calculates potential positions to generate traveling tracks for a target vehicle.

A mode switching unit transitions steering torque from normal to weak levels during autonomous lane change requests.

A vehicle control system transmits sensor data to a remote computer for parking space verification.

Machine learning models predict dynamic obstacle behavior to resolve collision risks, enabling reliable trajectory planning in complex traffic.

Convolutional neural network processes sensor data to resolve ambiguity in lighting state determination, enabling accurate trajectory generation.

Segmenting lateral and longitudinal planning reduces computational complexity while maintaining safety through formal stability analysis.

A dual vehicle fault processing system exchanges real-time data between independent devices to perform consistent fault determination and control actions.

A trajectory optimizer generates planned autonomous driving vehicle states using nonlinear optimization and road shape functions.

A control device estimates driver visual recognition timing to synchronize travel state changes.

Drones share personality traits to coordinate actions, resolving the trade-off between individual autonomy and swarm adaptability.

Machine programming adjusts autonomous vehicle driving parameters using priority levels to resolve inconsistent software updates across varying conditions.

Statistical correlation of detected objects between smart sensors enables self-service health monitoring, reducing hardware redundancy costs.

A vehicle computer compares local and remote identifiers to verify software consistency.

A position determining device selects unloading sides for autonomous vehicles based on delivery destination addresses and stopping attributes.

Segmenting coverage into discrete monitor zones reduces calculation burden while enhancing diagnostic precision for autonomous driving safety.

A cooperative smart lane selection system calculates flow factors across inter-lane zones to guide vehicles into kinematically similar lanes.

A vehicle control device adjusts entry conditions to facilitate smoother integration into circular intersections.

A vehicle control method uses a preset risk map to identify risky road segments and adjust driving states in real time.

Autonomous vehicles use spatial audio notifications to guide passengers during safe exit opportunities.

A vehicle size sensor detects oversized leading vehicles and modifies passing parameters to adjust lane change and speed.

A control system analyzes camera images to identify vehicles or occupants meeting predetermined conditions and outputs targeted commands.

A vehicle control system determines user proximity using portable device signal strength to initiate autonomous parking routines safely.

A model reference adaptive controller adjusts commands using time-delayed human operator feedback to determine stability limits.

A driving assistance device sets a standby area for turning vehicles based on object detection results.

An autonomy cognizant agent calculates policies mapping environment states to actions across multiple autonomy levels.

A vehicle platform uses qualitative models to process sensor data and generate conceptual neighborhood graphs for transparent autonomous decisions.

A carpool system verifies user attributes against riding conditions to prevent unauthorized vehicle access.

A neural network learns vehicle environment and behavior relationships to estimate driving conduct, resolving driver unease during autonomous transitions.

A cooperative autonomous driving strategy uses vehicle-to-vehicle communication to form coordination groups among vehicles.

A driver condition monitoring part detects face position relative to a camera angle of view and outputs movement information via an information providing system.

Processor saves environment map and timing data before SLAM tracking failure to restore accurate navigation state.

Autonomous air ambulance transports patients using vertical lift motors, resolving payload capacity versus power consumption trade-offs.

Selective archiving filters operational vehicle data using performance thresholds to isolate high-value segments, reducing storage and transmission costs.

Server apparatus dispatches autonomous mobile objects to capture real-time images of fleeing targets, eliminating response delays.

A vehicle control device detects lane markings by excluding regions where road continuity is interrupted from the recognition process.

A vehicle control apparatus uses overlapping detection ranges from two units to shift automation states based on object information match degrees.

Occupancy grid processing of present, past, and future radar data automates underdrivable region labeling, eliminating manual annotation costs.

Identification value calculation unit processes sensor data to detect dead reckoning faults.

A navigation system calculates estimated trajectory profiles by identifying directional portions controlling object travel vectors.

On-trip monitoring system assesses autonomous vehicle degradation levels using live log data to trigger service updates.

An autonomous vehicle requests altered traffic regulations from a governing authority to enable temporary deviations from standard rules.

Classifying wheel direction via a machine-learned model estimates trajectories faster, resolving the trade-off between prediction accuracy and processing time.

CNN error feedback quantifies lane detection uncertainty to resolve prediction accuracy trade-offs in autonomous driving.

A computer vision system detects occupants and adjusts vehicle components based on detected characteristics.

Dynamic buffer distances adapt to object velocity while segmented curvature optimization balances navigation smoothness with collision avoidance reliability.