Autonomous Decision Making Process TRIZ Cases

Fleet sensor data and remote classification help autonomous vehicles detect severe road impacts, avoid false service alerts, and route inspections.

Adaptive control modes adjust speed, trajectory, and user position to guide or follow people safely through crowded spaces.

An omega-shaped modular AGV lift platform uses pantograph lifting and movable accessories to improve ergonomic loading and unloading.

When GNSS signals drop out, a kinematic model uses steering angles and wheel speeds to keep a slipform paver on trajectory.

Sensors and package ID data coordinate panel opening and autonomous vehicle positioning to secure room-based package delivery.

Predefined human-AI task sequences cut remote AV response time by clarifying operator input, AI roles, and multi-agent task delegation.

Digital lane barriers use roadside sensing to predict lateral vehicle movement and protect reserved corridors without physical dividers.

When time between bookings is short, the robot sends lent equipment directly to the next use location instead of storage to keep it available.

A lane-specific coordinate model stays aligned through vehicle orientation changes, improving tracking when lane lines run perpendicular.

Authentication codes tied to a vehicle private key protect update and training-data transfers from tampering between the vehicle and host.

By linking vehicle load, tilt, acceleration, and position data, the mower detects pits, mud, and obstacles and maps them for maintenance.

Real-time output tracking and vehicle-specific offsets generate accurate companion guidance lines for baling and grain collection.

At busy pickup queues, riders choose a nearby autonomous vehicle and authenticate digitally to clarify assignment and reduce wait time.

Encrypted audio from a connected speaker guides autonomous carriers to the right drop-off spot when network access is unavailable.

Blended cooperative and non-cooperative sensor data improves UAV obstacle detection and avoidance when GPS and obstacle databases fall short.

Remote UAV inspection captures property damage data, avoids obstructions, and speeds insurance claim initiation with less manual field work.

Static obstruction data from drones and external sources is merged to guide route changes and collision avoidance in dense autonomous air traffic.

A displayed guideline links the harvester and target start point, helping operators judge position and begin automatic field travel smoothly.

Modular situation assessment, decision-making, and mission assignment help multi-UAV formations handle unstable links and fast-changing combat scenarios.

A mobile robot changes camera height and position to capture immersive multi-angle home views for remote monitoring and interaction.

Multiple virtual path boundaries from sensor and image data keep autonomous driving stable when lane lines are blocked or unclear.

Targeted sensor tasks let mobile units capture weak driving scenarios, cutting data collection time while improving automatic control models.

Pairwise loss and zeroed background scores help train neural networks to rank nearby agents more accurately with less computation.

Weighted fusion of radar, acoustic, visual, and GPS data helps UAVs detect non-cooperative obstacles and plan avoidance paths.

Directional acoustic sensing guides a drone to unknown sound sources when cameras fail, cutting weight and improving low-visibility response.

An ANN predicts access patterns and remaps data placement to reduce write amplification while preserving autonomous vehicle storage endurance.

A trained vision model links traffic lights to controlled lanes, enabling real-time lane-state decisions without map dependence or remote help.

Multiple mobility devices fuse sensor data into indoor maps with ramps and elevators, improving autonomous building navigation.

Flight-path planning tied to target map resolution enables UAV image capture and processing into real-time survey maps without offline delays.

Map-guided ROI exposure helps autonomous vehicle cameras keep pedestrians and traffic signs visible during sudden lighting changes.

User engagement with captured video is analyzed to adapt UAV flight and sensor settings, reducing manual tuning and improving content quality.

Dynamic anchor selection lets robotic agents switch between moving and stationary reference roles to limit drift and improve swarm localization without GPS.

A mobile robot retracts its wheel to sit stably at stops, cutting gyro power use while preserving expressive standing motion control.

An FSM-based dataflow mapping approach adapts multicore scheduling to QoS and power-budget changes, cutting power use in embedded image processing.

Camera images of laser beam intersections reveal scanner misalignment in mobile robots, enabling real-time correction to reduce collision risk.

Automatic tensor shape inference cuts manual shape specification, improves memory use, and enables optimized neural network code generation.

Multifocal sensors in VTOL landing feet build a 3D terrain map, helping the aircraft detect slopes and orient for stable autonomous landing.

Confidence-weighted sensor fusion helps UAVs resolve conflicting or untrusted inputs and trigger corrective mission actions in dynamic conditions.

Vehicle-guided placement of wireless toolboxes creates portable site coverage and monitoring where power and cellular signal are limited.

Vertically movable lifts and articulating arms let an AGV retrieve and place containers on high shelves while reducing manual carrying and ladder use.

A self-moving traffic control platform uses sensors and path control to place signs automatically, reducing manual setup, worker risk, and labor.

Dynamic zone reservation coordinates independent transport systems in shared logistics routes to prevent deadlocks and reduce manual intervention.

Multi-level managers abstract vehicle and section data to cut latency and guide connected vehicles through congestion and road events.

Five-stage vehicle data collection with dynamic alignment and figure-8 runs reduces low-cost sensor positioning error for accurate map building.

Future-demand sampling guides trip-vehicle assignment and routing, helping high-capacity ride-sharing fleets scale in real time with low wait delays.

Traffic participant state and path data help autonomous vehicles maintain timely positioning when GPS signals are weak, improving driving safety.

Location-linked sensor maps let autonomous robots target dirt, obstacles, and air quality zones to cut setup effort and task time.