A roadside communication device having a data relay function includes a communication unit that receives mobile object data whose generator is a mobile object; a determining unit that determines whether to perform a thinning process of an amount of the mobile object data received by the communication unit, based on a predetermined determination condition; and a relay unit that relays the mobile object data with the thinning process when a result of the determination by the determining unit is positive, and relays the mobile object data without the thinning process when the result of the determination by the determining unit is negative.

A set of incoming lanes are identified within a pre-determined proximity of a traffic signal as candidate lanes to receive a go-signal from the traffic signal. A prioritized overall lane wait time is calculated for each incoming lane. Selected lanes receive the go-signal in the current iteration, based on the prioritized overall lane wait time. An amount of time to allocate to the go-signal is calculated, based on the number of vehicles to flush from the selected lanes. The go-signal is presented to the selected lanes for the allocated time, including non-conflicting lanes. A set of metrics are collected including throughput of vehicles leaving the pre-determined proximity of the traffic signal. Based on the metrics, a time allocation is determined for the next iteration of the go-signal, parameters are updated for the prioritized overall lane wait time, and the next iteration of the traffic signal is initiated.

Data is received from each of a plurality of vehicles proximate to an intersection indicating a kinetic energy and a time to the intersection. An optimized timing of a traffic light is determined based on an aggregation of the kinetic energies and times to intersection. A timing of the traffic is modified according to the optimized timing.

A vehicle prioritization system is provided. The system includes a central controller. The central controller is configured to receive one or more characteristics of one or more vehicles, and the central controller is also configured to assign a priority for each of the one or more vehicles according to the one or more characteristics of each of the one or more vehicles. Movement of each of the one or more vehicles having a higher priority is prioritized over vehicles having a lower priority.

A lighting network (100) and methods therefore are disclosed. The lighting network (100) includes a plurality of lighting units (LU0-LU10) each including a wireless receiver (12) arranged to obtain a wireless signal from an object (30) to be tracked and a communication interface (14). The lighting network (100) also includes a control unit (20) including a communication unit (22) that is arranged to communicate with at least one of the plurality of lighting units (LU0-LU10) to obtain tracking data based upon the wireless signal. The tracking data is processed by the control unit (20) using a topology table (FIG. 1b). The topology table (FIG. 1b) is based upon the geographic locations of the plurality of lighting units and mapping data.

A lighting network (100) and methods therefore are disclosed. The lighting network (100) includes a plurality of lighting units (LU0-LU10) each including a wireless receiver (12) arranged to obtain a wireless signal from an object (30) to be tracked and a communication interface (14). The lighting network (100) also includes a control unit (20) including a communication unit (22) that is arranged to communicate with at least one of the plurality of lighting units (LU0-LU10) to obtain tracking data based upon the wireless signal. The tracking data is processed by the control unit (20) using a topology table (FIG. 1b). The topology table (FIG. 1b) is based upon the geographic locations of the plurality of lighting units and mapping data.

Proposed herein are a signal control apparatus and method. The signal control apparatus includes: a photographing unit configured to acquire a plurality of intersection images by capturing a plurality of intersections; a storage configured to store a program for the control of traffic signals; and a controller including at least one processor, and configured to calculate control information for the control of traffic lights at each of the plurality of intersections using the intersection images acquired through the photographing unit by executing the program. The controller calculates control information for the control of traffic lights at each of the plurality of intersections based on action information calculated by a plurality of agents by using a plurality of agents based on a reinforcement learning model trained by outputting action information for the control of traffic lights while using state information and a reward as input values.

Proposed herein are a signal control apparatus and method. The signal control apparatus includes: a photographing unit configured to acquire a plurality of intersection images by capturing a plurality of intersections; a storage configured to store a program for the control of traffic signals; and a controller including at least one processor, and configured to calculate control information for the control of traffic lights at each of the plurality of intersections using the intersection images acquired through the photographing unit by executing the program. The controller calculates control information for the control of traffic lights at each of the plurality of intersections based on action information calculated by a plurality of agents by using a plurality of agents based on a reinforcement learning model trained by outputting action information for the control of traffic lights while using state information and a reward as input values.

A system and method of multi-agent reinforcement learning for integrated and networked adaptive traffic controllers (MARLIN-ATC). Agents linked to traffic signals generate control actions for an optimal control policy based on traffic conditions at the intersection and one or more other intersections. The agent provides a control action considering the control policy for the intersection and one or more neighboring intersections. Due to the cascading effect of the system, each agent implicitly considers the whole traffic environment, which results in an overall optimized control policy.

A system and method of multi-agent reinforcement learning for integrated and networked adaptive traffic controllers (MARLIN-ATC). Agents linked to traffic signals generate control actions for an optimal control policy based on traffic conditions at the intersection and one or more other intersections. The agent provides a control action considering the control policy for the intersection and one or more neighboring intersections. Due to the cascading effect of the system, each agent implicitly considers the whole traffic environment, which results in an overall optimized control policy.