Autonomous Decision Making Process TRIZ Cases

A parking assistance device determines target positions using dynamic separation distances between detected obstacles.

Phased lidar sensors cover 360 degrees without gaps, resolving the trade-off between full coverage and synchronization complexity.

A behavior planner generates conditional action sequences using Monte Carlo Tree Search to optimize trajectory planning.

Centralized server coordinates autonomous vehicle parking and retrieval to reduce congestion.

An AI apparatus determines auto stop control modes using traffic data inputs.

Consolidating recurring feature transmissions reduces data volume while maintaining localization precision.

A controller directs agricultural machinery along optimized routes using aerial field data for efficient crop material pickup.

A mixed-mode driving system adjusts vehicle operation between autonomous and manual states using real-time sensor data.

System detects unidirectional parking lot lanes to permit automatic driving, reducing collision risk in complex environments.

Information processing device manages autonomous vehicle loading space to identify vacant sections during parcel delivery operations.

Automated driving control part determines and proposes driver assistance packages based on environment and vehicle data.

A vehicle control system adjusts autonomous authority levels using real-time sensor data and operator feedback to manage driving operations.

A neural network action model predicts vehicle states using sensor data to enhance autonomous driving control.

Tracking unit determines if an obstacle enters a blind spot area and clears detection after a second obstacle passes, preventing false recognition.

Navigation system assigns priority levels to vehicles and issues maneuver instructions to coordinate movement in mixed traffic environments.

A machine-learned motion planning system uses a unified cost function to jointly optimize behavioral and trajectory stages.

Sensors detect grab events to trigger autonomous standby mode, reducing manual control requirements.

A robotic vehicle uses camera and LIDAR sensors to map boundaries and navigate autonomously.

Machine learned models process top-down environmental data to predict object movements and assign weights to potential trajectories.

A quad-tree structure partitions solid angle bins to assign probability values for negative inverse sensor models in 3D environment mapping.

Universal modular robotic chassis resolves versatility trade-offs by swapping functional modules for tasks like food delivery.

A kingpin sensor mounted on the steering knuckle detects relative rotation, eliminating latency errors from upstream linkage monitoring.

A two-wheel automatic guided vehicle maintains upright orientation using motor controllers that adjust wheel speed based on tilt sensor data.

Vehicles exchange maneuver data to coordinate actions and reduce collision risks in adverse conditions.

Variable speed reception identifies high-priority packets by length, reducing processing time while maintaining identification accuracy.

Intelligent routing of sensor outputs via connectivity switches distributes processing tasks across domains, reducing latency and jitter in vehicular networks.

Patch neural networks resolve deep neural network failure modes via fusion mechanisms, eliminating validation downtime.

A laser range finder adjusts its light projection angle using polarization camera data to maintain orthogonal alignment with the road surface.

A path planning system adjusts trajectory length iteratively to generate valid routes for autonomous vehicles.

A vehicle steering system moves the rim rectilinearly via gears to adjust posture.

A vehicle control system adjusts operating strategies using sensor data and feedback loops to align with current driving conditions.

Radar sensors detect stationary scatterers to calculate linear and angular velocities, resolving latency issues in GPS and inertial measurement systems.

A checking device validates sensor data before autonomous driving operations to prevent collisions.

A recurrent neural network generates local region feature maps from camera images to predict surrounding vehicle maneuvers.

Computing device generates regular routes and transmits autonomous driving commands to vehicles, resolving manual route planning inefficiencies.

Vehicle management system determines pickup location using historical data patterns to resolve connectivity loss and reduce user waiting time.

A mobile device control system decomposes target relative velocity into translation and rotation components to generate autonomous movement laws.

A driving assist apparatus detects steering wheel release to transition between automation levels.

An information presentation apparatus calculates driver engagement levels based on activity determination and system confidence.

Dynamic vehicle clustering overcomes static advertisement limitations by adjusting routes and synchronizing displays for real-time audience engagement.

A lane change control device calculates traffic influence and sets position-dependent acceptable limits to execute maneuvers.

A computer system maneuvers an autonomous vehicle to target areas using a reinforcement learning reward function.

Computing system determines prior probability distributions of motion paths from historical sensor data to generate driving trajectories.

Code markings encode data via distance from lane lines, resolving space constraints while maintaining detection reliability.

Travel control apparatus increases driver participation when camera operations become unstable, resolving reliability issues in automated driving.

Self-driving vehicle system predicts nearby driver behavior using sensor data to adjust speed and position dynamically.

Preemptive braking resolves fuel efficiency versus collision avoidance contradictions by increasing following gaps before lead vehicle reactions.

LIDAR-based cabin monitoring determines occupant orientation and seat position to optimize airbag deployment strategies during collisions.

A drive assistance system evaluates sensor detection performance to specify decrease regions where accuracy declines.

A neural network processes user data from environmental sensors and mobile devices to tailor infotainment volume and driving style based on detected mood.