Obstacle detection systems and methods
Example obstacle detection systems and methods are described. In one implementation, a method receives data from at least one sensor mounted to a vehicle and creates a probabilistic grid-based map associated with an area near the vehicle. The method also determines a confidence associated with each probability in the grid-based map and determines a likelihood that an obstacle exists in the area near the vehicle based on the probabilistic grid-based map.
1. A method comprising:
receiving, by a controller of a vehicle, data from at least one sensor mounted to the vehicle;
creating, by an obstacle detection system executed by the controller, a probabilistic grid-based map associated with an area near the vehicle, the grid-based map defined as a two-dimensional array of cells distributed in a horizontal plane adjacent the vehicle;
determining, by the obstacle detection system, a confidence associated with each cell of the array of cells in the probabilistic grid-based map; and
determining, by the obstacle detection system, a likelihood that an obstacle exists in the area near the vehicle based on the probabilistic grid-based map;
performing temporal analysis of the received data using learning and forgetting factors associated with the probabilistic grid-based map;
wherein the learning factor increases a probability value associated with each cell in the array of cells over time; and
wherein the forgetting factor decreases a probability value associated with each cell in the array of cells over time.
2. The method of claim 1 , wherein the at least one sensor includes at least one of a LIDAR sensor, a radar sensor, and a camera.
3. The method of claim 1 , further comprising, responsive to determining a likelihood that an obstacle exists in the area near the vehicle, generating an alert to the driver of the vehicle.
4. The method of claim 1 , further comprising, responsive to determining a likelihood that an obstacle exists in the area near the vehicle, communicating an alert to an automated driving system of the vehicle.
5. The method of claim 1 , further comprising calculating probabilities associated with neighboring cells in the probabilistic grid-based map based on the received data.
6. The method of claim 5 , wherein the neighboring cells include eight cells immediately surrounding a particular cell in the probabilistic grid-based map.
7. The method of claim 5 , further comprising updating probabilistic values of the neighboring cells using a Bayesian method.
8. The method of claim 1 , wherein the vehicle is an autonomous vehicle.