The invention provides a lighting system (10) for generating a configurable spotlight effect adapted to direct the attention of an individual from an initial location (34) to a defined second location (36). In particular, the invention comprises a presence detector (14) for detecting motion of an individual (22) at a detection location (28) within a detection area, and for detecting in which direction the individual (22) is moving. A configurable light source (12) is controlled by a controller (18) to create a light effect (30, 32) from a first location (34) in front of the individual (22) based on the direction of the individual (22) toward a defined location (36) so as to thereby draw the attention of the user toward said defined location.

An apparatus includes a classification of shaded area and a light unit being configured for illumination. A solar panel is configured for at least providing an energy output during exposure of shade being classified by the classification of shaded area. A rechargeable storage device is configured for storing at least a portion of the energy output as stored energy. The stored energy recharges the rechargeable storage device. A safety device is configured for at least protecting the rechargeable storage device from substantial overcharging during exposure of direct sunlight. A cutoff threshold is configured for at least preventing a deep discharging of the rechargeable storage device. An illumination mode comprises at least the rechargeable storage device providing the stored energy, the light unit providing the illumination, the illumination lasting for at least 5 hours, and the cutoff threshold preventing the deep discharging of the rechargeable storage device.

Technologies are described to provide control of traffic signals based at least in part on multiple Q-learning categories. In some examples, a method may include clustering historical traffic data into multiple traffic pattern clusters, and generating multiple Q-learning categories, where each Q-learning category corresponds to a traffic pattern cluster of the multiple traffic pattern clusters. The method may also include determining a first Q-learning category of the multiple Q-learning categories to use in controlling traffic signals at an intersection based at least in part on a first traffic data of the intersection, where the first Q-learning category corresponds to a first traffic pattern cluster, and the first traffic data corresponds to the first traffic pattern cluster. The method may additionally include generating a first control action for the traffic signals at the intersection based at least in part on the first Q-learning category.

Disclosed is a light guide mat (1) for the production of a block- or cuboid-shaped light guide body (21), which mat is arranged in a casting mold and can be sealed in a pourable, curable casting compound (24), wherein the light guide mat (1) consists of longitudinal and transverse struts (2, 3) connected to one another in the form of a grid, which struts consist at least partially of a light-conducting plastic, wherein profiled light guide elements (4) consisting of an at least partially light-conducting plastic are integrally formed at the point of intersection of the longitudinal and transverse struts (2, 3), an end face (6) of which elements being formed as light-emitting surfaces on the upper face (22) of the light guide body (21), wherein at least the longitudinal struts (2) of the light guide mat (1) are formed as light channels (5) for receiving point-like, light-generating elements, and the light channels (5) are integrally formed on the face of the light guide elements (4) near to the bottom.

A modular lighting system may include a support structure, a plurality of heat sink modules physically supported by the support structure, and one or more light source modules coupled to the plurality of heat sink modules. The plurality of heat sink modules may be arranged in a modular manner such that the number of heat sink modules in the modular lighting system is variable, and each heat sink module may be an integral molded structure defining at least one opening or passageway.

The system includes at least one light projector designed for focused projection of the image onto the surface of the road crossing. The light projector is connected with the control unit and is designed for projection of various images onto the persons and road in the place of crossing. The image from the light projector includes circles, polygons, strips, squares, rectangles, and combinations thereof, which are separated by surfaces of different color or different level of illumination. There are sharp, contrasting boundaries between individual, usually repeating elements of the image. In the preferable arrangement the system includes at least one sensor of the physical values of the environment connected to the control unit and eventually a camera and/or vehicle speed sensor and/or sensor of physiological values of the persons in the vicinity of the road crossing, too. The system can include a speaker connected to the control unit.

Technologies are described to provide control of traffic signals based at least in part on multiple Q-learning categories. In some examples, a method may include clustering historical traffic data into multiple traffic pattern clusters, and generating multiple Q-learning categories, where each Q-learning category corresponds to a traffic pattern cluster of the multiple traffic pattern clusters. The method may also include determining a first Q-learning category of the multiple Q-learning categories to use in controlling traffic signals at an intersection based at least in part on a first traffic data of the intersection, where the first Q-learning category corresponds to a first traffic pattern cluster, and the first traffic data corresponds to the first traffic pattern cluster. The method may additionally include generating a first control action for the traffic signals at the intersection based at least in part on the first Q-learning category.

Technologies are described to adjust a learning rate of Q-learning being used to control traffic signals at an intersection. In some examples, a method may include generating control actions for traffic signals at an intersection based on Q-learning, determining a frequency of change in traffic pattern of the intersection, and adjusting a learning rate of the Q-learning based on the determined frequency of change in traffic pattern of the intersection. The Q-learning may determine the generated control actions based on at least a portion of historical traffic data of the intersection, and the change in traffic pattern may be a change from a first traffic pattern of the intersection to a second traffic pattern of the intersection.

A lighting system is provided. The lighting system includes a light source. A wavelength converter is configured to convert a wavelength of light emitted from the light source. A light guide tube is configured to propagate and transmit incoherent light emitted from the wavelength converter. The light guide tube extends along a road.

A crosswalk lighting arrangement is provided. The arrangement includes a light source, securing hardware configured to secure the light source above a position between the center line of the crosswalk and a predetermined position in the direction of oncoming traffic and at a predetermined height above the crosswalk, and protective shielding configured to block and direct light energy from the light source to a predetermined range relative to the crosswalk forward border and the crosswalk rear border. The light source generates light energy at a minimum of 30 lux of vertical luminance.