All the sensors use the UE coordinate system (__x__-*forward*, __y__-*right*, __z__-*up*), and return coordinates in local space. When using any visualization software, pay attention to its coordinate system. Many invert the Y-axis, so visualizing the sensor data directly may result in mirrored outputs.
This sensor registers an event each time its parent actor collides against something in the world. Each collision sensor produces one collision event per collision per frame. Multiple collision events may be produced in a single frame by collisions with multiple other actors. To ensure that collisions with any kind of object are detected, the server creates "fake" actors for elements such as buildings or bushes so the semantic tag can be retrieved to identify it.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `actor` | [carla.Actor](<../python_api#carlaactor>) | Actor that measured the collision (sensor's parent). |
| `other_actor` | [carla.Actor](<../python_api#carlaactor>) | Actor against whom the parent collided. |
| `normal_impulse` | [carla.Vector3D](<../python_api#carlavector3d>) | Normal impulse result of the collision. |
The camera provides a raw data of the scene codifying the distance of each pixel to the camera (also known as **depth buffer** or **z-buffer**) to create a depth map of the elements.
The image codifies depth value per pixel using 3 channels of the RGB color space, from less to more significant bytes: _R -> G -> B_. The actual distance in meters can be
The output [carla.Image](python_api.md#carla.Image) should then be saved to disk using a [carla.colorConverter](python_api.md#carla.ColorConverter) that will turn the distance stored in RGB channels into a __[0,1]__ float containing the distance and then translate this to grayscale.
There are two options in [carla.colorConverter](python_api.md#carla.ColorConverter) to get a depth view: __Depth__ and __Logaritmic depth__. The precision is milimetric in both, but the logarithmic approach provides better results for closer objects.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `width` | int | Image width in pixels. |
| `height` | int | Image height in pixels. |
| `fov` | float | Horizontal field of view in degrees. |
Reports current [gnss position](https://www.gsa.europa.eu/european-gnss/what-gnss) of its parent object. This is calculated by adding the metric position to an initial geo reference location defined within the OpenDRIVE map definition.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `latitude` | double | Latitude of the actor. |
| `longitude` | double | Longitude of the actor. |
Provides measures that accelerometer, gyroscope and compass would retrieve for the parent object. The data is collected from the object's current state.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `accelerometer` | [carla.Vector3D](<../python_api#carlavector3d>) | Measures linear acceleration in `m/s^2`. |
Registers an event each time its parent crosses a lane marking.
The sensor uses road data provided by the OpenDRIVE description of the map to determine whether the parent vehicle is invading another lane by considering the space between wheels.
However there are some things to be taken into consideration:
* Discrepancies between the OpenDRIVE file and the map will create irregularities such as crossing lanes that are not visible in the map.
* The output retrieves a list of crossed lane markings: the computation is done in OpenDRIVE and considering the whole space between the four wheels as a whole. Thus, there may be more than one lane being crossed at the same time.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `actor` | [carla.Actor](<../python_api#carlaactor>) | Vehicle that invaded another lane (parent actor). |
| `crossed_lane_markings` | list([carla.LaneMarking](<../python_api#carlalanemarking>)) | List of lane markings that have been crossed. |
The points are computed by adding a laser for each channel distributed in the vertical FOV. The rotation is simulated computing the horizontal angle that the Lidar rotated in a frame. The point cloud is calculated by doing a ray-cast for each laser in every step.
A LIDAR measurement contains a package with all the points generated during a `1/FPS` interval. During this interval the physics are not updated so all the points in a measurement reflect the same "static picture" of the scene.
This output contains a cloud of simulation points and thus, it can be iterated to retrieve a list of their [`carla.Location`](python_api.md#carla.Location):
The information of the LIDAR measurement is encoded 4D points. Being the first three, the space points in xyz coordinates and the last one intensity loss during the travel. This intensity is computed by the following formula.
`a` — Attenuation coefficient. This may depend on the sensor's wavelenght, and the conditions of the atmosphere. It can be modified with the LIDAR attribute `atmosphere_attenuation_rate`.
For a better realism, points in the cloud can be dropped off. This is an easy way to simulate loss due to external perturbations. This can done combining two different.
*__General drop-off__ — Proportion of points that are dropped off randomly. This is done before the tracing, meaning the points being dropped are not calculated, and therefore improves the performance. If `dropoff_general_rate = 0.5`, half of the points will be dropped.
*__Instensity-based drop-off__ — For each point detected, and extra drop-off is performed with a probability based in the computed intensity. This probability is determined by two parameters. `dropoff_zero_intensity` is the probability of points with zero intensity to be dropped. `dropoff_intensity_limit` is a threshold intensity above which no points will be dropped. The probability of a point within the range to be dropped is a linear proportion based on these two parameters.
Additionally, the `noise_stddev` attribute makes for a noise model to simulate unexpected deviations that appear in real-life sensors. For positive values, each point is randomly perturbed along the vector of the laser ray. The result is a LIDAR sensor with perfect angular positioning, but noisy distance measurement.
The rotation of the LIDAR can be tuned to cover a specific angle on every simulation step (using a [fixed time-step](adv_synchrony_timestep.md)). For example, to rotate once per step (full circle output, as in the picture below), the rotation frequency and the simulated FPS should be equal. <br>__1.__ Set the sensor's frequency `sensors_bp['lidar'][0].set_attribute('rotation_frequency','10')`. <br>__2.__ Run the simulation using `python3 config.py --fps=10`.
| `atmosphere_attenuation_rate` | float | 0.004 | Coefficient that measures the LIDAR instensity loss per meter. Check the intensity computation above. |
| `dropoff_general_rate` | float | 0.45 | General proportion of points that are randomy dropped. |
| `dropoff_intensity_limit` | float | 0.8 | For the intensity based drop-off, the threshold intensity value above which no points are dropped. |
| `dropoff_zero_intensity` | float | 0.4 | For the intensity based drop-off, the probability of each point with zero intensity being dropped. |
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `horizontal_angle` | float | Angle (radians) in the XY plane of the LIDAR in the current frame. |
| `channels` | int | Number of channels (lasers) of the LIDAR. |
| `get_point_count(channel)` | int | Number of points per channel captured this frame. |
| `raw_data` | bytes | Array of 32-bits floats (XYZI of each point). |
To ensure that collisions with any kind of object are detected, the server creates "fake" actors for elements such as buildings or bushes so the semantic tag can be retrieved to identify it.
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `actor` | [carla.Actor](<../python_api#carlaactor>) | Actor that detected the obstacle (parent actor). |
| `other_actor` | [carla.Actor](<../python_api#carlaactor>) | Actor detected as an obstacle. |
| `distance` | float | Distance from `actor` to `other_actor`. |
The sensor creates a conic view that is translated to a 2D point map of the elements in sight and their speed regarding the sensor. This can be used to shape elements and evaluate their movement and direction. Due to the use of polar coordinates, the points will concentrate around the center of the view.
Points measured are contained in [carla.RadarMeasurement](python_api.md#carla.RadarMeasurement) as an array of [carla.RadarDetection](python_api.md#carla.RadarDetection), which specifies their polar coordinates, distance and velocity.
The provided script `manual_control.py` uses this sensor to show the points being detected and paint them white when static, red when moving towards the object and blue when moving away:
| `bloom_intensity` | float | 0\.675 | Intensity for the bloom post-process effect, `0.0` for disabling it. |
| `fov` | float | 90\.0 | Horizontal field of view in degrees. |
| `fstop` | float | 1\.4 | Opening of the camera lens. Aperture is `1/fstop` with typical lens going down to f/1.2 (larger opening). Larger numbers will reduce the Depth of Field effect. |
| `image_size_x` | int | 800 | Image width in pixels. |
| `image_size_y` | int | 600 | Image height in pixels. |
| `iso` | float | 100\.0 | The camera sensor sensitivity. |
| `gamma` | float | 2\.2 | Target gamma value of the camera. |
| `lens_flare_intensity` | float | 0\.1 | Intensity for the lens flare post-process effect, `0.0` for disabling it. |
| `min_fstop` | float | 1\.2 | Maximum aperture. |
| `blade_count` | int | 5 | Number of blades that make up the diaphragm mechanism. |
| `exposure_mode` | str | `histogram` | Can be `manual` or `histogram`. More in [UE4 docs](<https://docs.unrealengine.com/en-US/Engine/Rendering/PostProcessEffects/AutomaticExposure/index.html>). |
| `exposure_min_bright` | float | 10\.0 | In `exposure_mode: "histogram"`. Minimum brightness for auto exposure. The lowest the eye can adapt within. Must be greater than 0 and less than or equal to `exposure_max_bright`. |
| `exposure_max_bright` | float | 12\.0 | In \`exposure\_mode: "histogram"\`. Maximum brightness for auto exposure. The highestthe eye can adapt within. Must be greater than 0 and greater than or equal to \`exposure\_min\_bright\`. |
| `motion_blur_max_distortion` | float | 0\.35 | Max distortion caused by motion blur. Percentage of screen width. |
| `motion_blur_min_object_screen_size` | float | 0\.1 | Percentage of screen width objects must have for motion blur, lower value means less draw calls. |
| `slope` | float | 0\.88 | Steepness of the S-curve for the tonemapper. Larger values make the slope steeper (darker) [0.0, 1.0]. |
| `toe` | float | 0\.55 | Adjusts dark color in the tonemapper [0.0, 1.0]. |
| `shoulder` | float | 0\.26 | Adjusts bright color in the tonemapper [0.0, 1.0]. |
| `black_clip` | float | 0\.0 | This should NOT be adjusted. Sets where the crossover happens and black tones start to cut off their value [0.0, 1.0]. |
| `white_clip` | float | 0\.04 | Set where the crossover happens and white tones start to cut off their value. Subtle change in most cases [0.0, 1.0]. |
| `temp` | float | 6500\.0 | White balance in relation to the temperature of the light in the scene. **White light:** when this matches light temperature. **Warm light:** When higher than the light in the scene, it is a yellowish color. **Cool light:** When lower than the light. Blueish color. |
| `tint` | float | 0\.0 | White balance temperature tint. Adjusts cyan and magenta color ranges. This should be used along with the white balance Temp property to get accurate colors. Under some light temperatures, the colors may appear to be more yellow or blue. This can be used to balance the resulting color to look more natural. |
| `chromatic_aberration_intensity` | float | 0\.0 | Scaling factor to control color shifting, more noticeable on the screen borders. |
| `chromatic_aberration_offset` | float | 0\.0 | Normalized distance to the center of the image where the effect takes place. |
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `width` | int | Image width in pixels. |
| `height` | int | Image height in pixels. |
| `fov` | float | Horizontal field of view in degrees. |
This sensor integrates the [C++ Library for Responsibility Sensitive Safety](https://github.com/intel/ad-rss-lib) in CARLA. It is disabled by default in CARLA, and it has to be explicitly built in order to be used.
The RSS sensor calculates the RSS state of a vehicle and retrieves the current RSS Response as sensor data. The [carla.RssRestrictor](python_api.md#carla.RssRestrictor) will use this data to adapt a [carla.VehicleControl](python_api.md#carla.VehicleControl) before applying it to a vehicle.
These controllers can be generated by an *Automated Driving* stack or user input. For instance, hereunder there is a fragment of code from `PythonAPI/examples/rss/manual_control_rss.py`, where the user input is modified using RSS when necessary.
The blueprint for this sensor has no modifiable attributes. However, the [carla.RssSensor](python_api.md#carla.RssSensor) object that it instantiates has attributes and methods that are detailed in the Python API reference. Here is a summary of them.
| `ego_vehicle_dynamics` | [ad.rss.world.RssDynamics](<https://intel.github.io/ad-rss-lib/ad_rss/Appendix-ParameterDiscussion/>) | RSS parameters to be applied for the ego vehicle |
| `other_vehicle_dynamics` | [ad.rss.world.RssDynamics](<https://intel.github.io/ad-rss-lib/ad_rss/Appendix-ParameterDiscussion/>) | RSS parameters to be applied for the other vehicles |
| `pedestrian_dynamics` | [ad.rss.world.RssDynamics](<https://intel.github.io/ad-rss-lib/ad_rss/Appendix-ParameterDiscussion/>) | RSS parameters to be applied for pedestrians |
| `road_boundaries_mode` | [carla.RssRoadBoundariesMode](<../python_api#carlarssroadboundariesmode>) | Enables/Disables the [stay on road](<https://intel.github.io/ad-rss-lib/ad_rss_map_integration/HandleRoadBoundaries>) feature. Default is **Off**. |
This sensor works fully on the client side. There is no blueprint in the server. Changes on the attributes will have effect __after__ the *listen()* has been called.
The methods available in this class are related to the routing of the vehicle. RSS calculations are always based on a route of the ego vehicle through the road network.
The sensor allows to control the considered route by providing some key points, which could be the [carla.Transform](python_api.md#carla.Transform) in a [carla.Waypoint](python_api.md#carla.Waypoint). These points are best selected after the intersections to force the route to take the desired turn.
| `response_valid` | bool | Validity of the response data. |
| `proper_response` | [ad.rss.state.ProperResponse](<https://intel.github.io/ad-rss-lib/doxygen/ad_rss/structad_1_1rss_1_1state_1_1ProperResponse.html>) | Proper response that the RSS calculated for the vehicle including acceleration restrictions. |
| `rss_state_snapshot` | [ad.rss.state.RssStateSnapshot](<https://intel.github.io/ad-rss-lib/doxygen/ad_rss/structad_1_1rss_1_1state_1_1RssStateSnapshot.html>) | RSS states at the current point in time. This is the detailed individual output of the RSS calclulations. |
| `situation_snapshot` | [ad.rss.situation.SituationSnapshot](<https://intel.github.io/ad-rss-lib/doxygen/ad_rss/structad_1_1rss_1_1situation_1_1SituationSnapshot.html>) | RSS situation at the current point in time. This is the processed input data for the RSS calclulations. |
| `world_model` | [ad.rss.world.WorldModel](<https://intel.github.io/ad-rss-lib/doxygen/ad_rss/structad_1_1rss_1_1world_1_1WorldModel.html>) | RSS world model at the current point in time. This is the input data for the RSS calculations. |
| `ego_dynamics_on_route` | [carla.RssEgoDynamicsOnRoute](<../python_api#carlarssegodynamicsonroute>) | Current ego vehicle dynamics regarding the route. |
This sensor simulates a rotating LIDAR implemented using ray-casting that exposes all the information about the raycast hit. Its behaviour is quite similar to the [LIDAR sensor](#lidar-sensor), but there are two main differences between them.
The points are computed by adding a laser for each channel distributed in the vertical FOV. The rotation is simulated computing the horizontal angle that the LIDAR rotated in a frame. The point cloud is calculated by doing a ray-cast for each laser in every step.
A LIDAR measurement contains a package with all the points generated during a `1/FPS` interval. During this interval the physics are not updated so all the points in a measurement reflect the same "static picture" of the scene.
This output contains a cloud of lidar semantic detections and therefore, it can be iterated to retrieve a list of their [`carla.SemanticLidarDetection`](python_api.md#carla.SemanticLidarDetection):
The rotation of the LIDAR can be tuned to cover a specific angle on every simulation step (using a [fixed time-step](adv_synchrony_timestep.md)). For example, to rotate once per step (full circle output, as in the picture below), the rotation frequency and the simulated FPS should be equal. <br>
__1.__ Set the sensor's frequency `sensors_bp['lidar'][0].set_attribute('rotation_frequency','10')`. <br>
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `horizontal_angle` | float | Angle (radians) in the XY plane of the LIDAR in the current frame. |
| `channels` | int | Number of channels (lasers) of the LIDAR. |
| `get_point_count(channel)` | int | Number of points per channel captured in the current frame. |
| `raw_data` | bytes | Array containing the point cloud with instance and semantic information. For each point, four 32-bits floats are stored. <br> XYZ coordinates. <br> cosine of the incident angle. <br> Unsigned int containing the index of the object hit. <br> Unsigned int containing the semantic tag of the object it. |
This camera classifies every object in sight by displaying it in a different color according to its tags (e.g., pedestrians in a different color than vehicles).
When the simulation starts, every element in scene is created with a tag. So it happens when an actor is spawned. The objects are classified by their relative file path in the project. For example, meshes stored in `Unreal/CarlaUE4/Content/Static/Pedestrians` are tagged as `Pedestrian`.
The server provides an image with the tag information __encoded in the red channel__: A pixel with a red value of `x` belongs to an object with tag `x`.
This raw [carla.Image](python_api.md#carla.Image) can be stored and converted it with the help of __CityScapesPalette__ in [carla.ColorConverter](python_api.md#carla.ColorConverter) to apply the tags information and show picture with the semantic segmentation.
| `0` | Unlabeled | `(0, 0, 0)` | Elements that have not been categorized are considered `Unlabeled`. This category is meant to be empty or at least contain elements with no collisions. |
| `1` | Roads | `(128, 64, 128)` | Part of ground on which cars usually drive. <br> E.g. lanes in any directions, and streets. |
| `2` | SideWalks | `(244, 35, 232)` | Part of ground designated for pedestrians or cyclists. Delimited from the road by some obstacle (such as curbs or poles), not only by markings. This label includes a possibly delimiting curb, traffic islands (the walkable part), and pedestrian zones. |
| `3` | Building | `(70, 70, 70)` | Buildings like houses, skyscrapers,... and the elements attached to them. <br> E.g. air conditioners, scaffolding, awning or ladders and much more. |
| `4` | Wall | `(102, 102, 156)` | Individual standing walls. Not part of a building. |
| `5` | Fence | `(190, 153, 153)` | Barriers, railing, or other upright structures. Basically wood or wire assemblies that enclose an area of ground. |
| `6` | Pole | `(153, 153, 153)` | Small mainly vertically oriented pole. If the pole has a horizontal part (often for traffic light poles) this is also considered pole. <br> E.g. sign pole, traffic light poles. |
| `7` | TrafficLight | `(250, 170, 30)` | Traffic light boxes without their poles. |
| `8` | TrafficSign | `(220, 220, 0)` | Signs installed by the state/city authority, usually for traffic regulation. This category does not include the poles where signs are attached to. <br> E.g. traffic- signs, parking signs, direction signs... |
| `9` | Vegetation | `(107, 142, 35)` | Trees, hedges, all kinds of vertical vegetation. Ground-level vegetation is considered `Terrain`. |
| `10` | Terrain | `(152, 251, 152)` | Grass, ground-level vegetation, soil or sand. These areas are not meant to be driven on. This label includes a possibly delimiting curb. |
| `11` | Sky | `(70, 130, 180)` | Open sky. Includes clouds and the sun. |
| `12` | Pedestrian | `(220, 20, 60)` | Humans that walk |
| `13` | Rider | `(255, 0, 0)` | Humans that ride/drive any kind of vehicle or mobility system <br> E.g. bicycles or scooters, skateboards, horses, roller-blades, wheel-chairs, etc. . |
| `20` | Static | `(110, 190, 160)` | Elements in the scene and props that are immovable. <br> E.g. fire hydrants, fixed benches, fountains, bus stops, etc. |
| `21` | Dynamic | `(170, 120, 50)` | Elements whose position is susceptible to change over time. <br> E.g. Movable trash bins, buggies, bags, wheelchairs, animals, etc. |
| `22` | Other | `(55, 90, 80)` | Everything that does not belong to any other category. |
| `23` | Water | `(45, 60, 150)` | Horizontal water surfaces. <br> E.g. Lakes, sea, rivers. |
| `24` | RoadLine | `(157, 234, 50)` | The markings on the road. |
| `25` | Ground | `(81, 0, 81)` | Any horizontal ground-level structures that does not match any other category. For example areas shared by vehicles and pedestrians, or flat roundabouts delimited from the road by a curb. |
| `26` | Bridge | `(150, 100, 100)` | Only the structure of the bridge. Fences, people, vehicles, an other elements on top of it are labeled separately. |
| `27` | RailTrack | `(230, 150, 140)` | All kind of rail tracks that are non-drivable by cars. <br> E.g. subway and train rail tracks. |
| `28` | GuardRail | `(180, 165, 180)` | All types of guard rails/crash barriers. |
*__Output:__ [carla.Image](python_api.md#carla.Image) per step (unless `sensor_tick` says otherwise).
This camera classifies every object in the field of view both by class and also by instance ID.
When the simulation starts, every element in scene is created with a tag. So it happens when an actor is spawned. The objects are classified by their relative file path in the project. For example, meshes stored in `Unreal/CarlaUE4/Content/Static/Pedestrians` are tagged as `Pedestrian`.
The server provides an image with the tag information __encoded in the red channel__: A pixel with a red value of `x` belongs to an object with tag `x`. The green and blue values of the pixel define the object's unique ID. For example a pixel with an 8 bit RGB value of [10, 20, 55] is a vehicle (Semantic tag 10) with a unique instance ID `20-55`.
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
versus 60 dB), no motion blur, and high temporal resolution (in the order of microseconds). Event cameras are thus sensors that can provide high-quality
visual information even in challenging high-speed scenarios and high dynamic range environments, enabling new application domains for vision-based
The provided script [`manual_control.py`][manual_control] uses the DVS camera in order to show how to configure the sensor, how to get the stream of events and how to depict such events in an image format, usually called event frame.
Note that due to the sampling method of the DVS camera, if there is no pixel difference between two consecutive synchronous frames the camera will not return an image. This will always occur in the first frame, as there is no previous frame to compare to and also in the event that there has been no movement between frames.
DVS is a camera and therefore has all the attributes available in the RGB camera. Nevertheless, there are few attributes exclusive to the working principle of an Event camera.
| `positive_threshold` | float | 0\.3 | Positive threshold C associated to a increment in brightness change (0-1). |
| `negative_threshold` | float | 0\.3 | Negative threshold C associated to a decrement in brightness change (0-1). |
| `sigma_positive_threshold` | float | 0 | White noise standard deviation for positive events (0-1). |
| `sigma_negative_threshold` | float | 0 | White noise standard deviation for negative events (0-1). |
| `refractory_period_ns` | int | 0\.0 | Refractory period (time during which a pixel cannot fire events just after it fired one), in nanoseconds. It limits the highest frequency of triggering events. |
| `use_log` | bool | true | Whether to work in the logarithmic intensity scale. |
| `log_eps` | float | 0\.001 | Epsilon value used to convert images to log: `L = log(eps + I / 255.0)`.<br> Where `I` is the grayscale value of the RGB image: <br>`I = 0.2989*R + 0.5870*G + 0.1140*B`. |
The Optical Flow camera captures the motion perceived from the point of view of the camera. Every pixel recorded by this sensor encodes the velocity of that point projected to the image plane. The velocity of a pixel is encoded in the range [-2,2]. To obtain the motion in pixel units, this information can be scaled with the image size to [-2 * image_size, 2 * image_size].
#### Optical Flow camera attributes
| Blueprint attribute | Type | Default | Description |
| `frame` | int | Frame number when the measurement took place. |
| `timestamp` | double | Simulation time of the measurement in seconds since the beginning of the episode. |
| `transform` | [carla.Transform](<../python_api#carlatransform>) | Location and rotation in world coordinates of the sensor at the time of the measurement. |
| `width` | int | Image width in pixels. |
| `height` | int | Image height in pixels. |
| `fov` | float | Horizontal field of view in degrees. |
| `raw_data` | bytes | Array of BGRA 64-bit pixels containing two float values. |
Vehicle-to-everything (V2X) communication is an important aspect for future applications of cooperative intelligent transportation systems. In real vehicles, this requires a dedicated onboard unit (OBU) in each vehicle, that is able to send and receive information over wireless channels. Depending on the region (Europe, China, USA), different physical technologies, protocols and application messaging formats are used.
CARLA currently supports simulation of a simple broadcast wireless channel and two application messages. Protocols for network access and forwarding are not supported yet. The two implemented messages are the [*Cooperative Awarness Message*](#cooperative-awareness-message) according to the European standard ETSI, and a [*custom message*](#custom-v2x-message) type, that can be used to transmit arbitrary string data (e.g. JSON). There are two distinct sensors for V2X communication, that can be used separately, one for each application message type.
Basically, the wireless channel incorporates the following calculation for both sensors:
ReceivedPower = OtherTransmitPower + combined_antenna_gain - loss
IF (ReceivedPower >= receiver_sensitivity)
THEN message is received
To simulate V2X communication, at least two V2X sensors of the same type need to be spawned (at least one sender-receiver pair). Because the received power is calculated on the receiver-side V2X sensor, only the antenna gain that is specified on the receiver-side sensor is incorporated in this calculation. Transmission power and receiver sensitivity can be configured (see [Blueprint attributes](#v2x-sensors-blueprint-attributes)).
The *loss* calculation depends on
- the visbility condition between sender and receiver: line of sight (no obstacles), non-line of sight obstructed by buildings, or non-line of sight obstructed by vehicles, and
- the scenario: highway, rural, or urban environment
While the visibility is simulated within CARLA, the scenario can be configured by the user (see [Blueprint attributes](#v2x-sensors-blueprint-attributes)), as well as several other attributes of the wireless channel.
### Sensor (sub)types
#### Cooperative Awareness Message
*__Blueprint:__ sensor.other.v2x
*__Output:__ [carla.CAMData](python_api.md#carla.CAMData), triggered according to the ETSI CAM standard, unless configured otherwise
Triggering conditions according to ETSI standard:
- Heading angle change > $4$°
- Position difference > $4$ m
- Speed change > $5$ m/s
- Time elapsed > CAM Generation time (configurable)
- Low Frequency Container Time Elapsed $> 500$ ms
For the CAM V2X sensor, additional blueprint attributes apply:
| Blueprint attribute | Type | Default | Description |
The function the user has to call every time to send a message. This function needs for an argument containing an object type [carla.SensorData](#carla.SensorData) to work with.
- **Parameters:**
-`data` (_function_) - The called function with one argument containing the sensor data.
The custom V2X message sensor works a little bit different than other sensors, because it has the *send* function in addition to the *listen* function, that needs to be called, before another sensor of this type will receive anything. The transmission of a custom message is only triggered, when *send* is called. Each message given to the *send* function is only transmitted once to all Custom V2X Message sensors currently spawned.
Example:
bp = world.get_blueprint_library().find('sensor.other.v2x_custom')
| frequency\_ghz | float | $5.9$ | Transmission frequency in GHz. 5.9 GHz is standard for several physical channels. |
| noise\_seed | int | $0$ | Random parameter for initialization of noise |
| filter\_distance | float | $500$ | Maximum transmission distance in meter, path loss calculations above are skipped for simulation speed |
| <tdcolspan=4>__Path loss model parameters__ |
| combined\_antenna\_gain | float | $10.0$ | Combined gain of sender and receiver antennas in dBi, parameter for radiation efficiency and directivity |
| d\_ref | float | $ 1.0 $ | reference distance for Log-distance path loss model in meter |
| path\_loss\_exponent | float | 2.7 | Loss parameter for non-line of sight due to building obstruction |
