Bosch presents innovative collision warning system for forklifts at the LogiMAT

0

The risks associated with the use of forklifts are often underestimated. According to the German statutory accident insurance, more than 13,500 accidents involving personal injury and the involvement of forklifts were reported in 2020 alone.

To avoid accidents, a new multi-camera-based collision warning system from Bosch helps to minimize the risk of accidents and relieves the driver by improving the overview of the entire vehicle and actively warning the driver of impending collisions.

The solution can be seen at the Bosch booth at the LogiMAT, which takes place from May 31 to June 2 at the Stuttgart exhibition center.

“With this system, we are making an important contribution to increasing safety when using forklifts and reducing the health risks for the driver,” says Stefan Schenk, who is responsible for off-road at Robert Bosch GmbH.

Multi-camera system with active warning

The new assistance system consists of four compact close-range cameras and a control unit that creates an all-round view of the vehicle’s surroundings and displays it to the forklift driver on a monitor. Depending on the driver’s current need for information, different views can be selected and shown on a display in full-screen format or in a split-screen layout. In addition, the driver can choose from a variety of view modes such as showing the road ahead or virtual camera pans.

The visual assistant presented at LogiMAT 2019 already provides good all-round visibility in the blind spot when the load on the fork blocks the driver’s view. With the extension, the system now also warns of stationary or moving objects in the vehicle’s surroundings with a color marking on the monitor and an acoustic signal in dangerous situations. For this purpose, three characteristic and particularly dangerous driving scenarios were identified and corresponding use cases for the warning function were derived. When driving into an aisle or past rows of shelves, the forklift driver is shown all the people who are kneeling, standing or moving in front of or next to the vehicle.

If the system recognizes that an intersection is approaching, it switches to intersection mode and also warns the driver of people or vehicles approaching from the side. Another advantage of the new assistance system is the warning function, which supports the driver when handling stored goods. The detection is then aimed at people who are moving at a distance of 4m relative to the vehicle.

Object recognition with neural networks

Two analysis methods, object detection and object recognition, are combined so that the system can reliably detect imminent collisions and only warn of relevant accident risks. With object detection, the system logic uses characteristic movements to decide whether an object is relevant for the collision warning or not. With object detection, the decision is made based on the shape of the object. To do this, the image of the object is automatically compared with stored image patterns.

“This is ensured by so-called neural networks, a software architecture from the field of artificial intelligence that are trained to recognize certain visual patterns,” says Schenk. “By combining the two measurement principles, it is ensured that the three situations with a potentially critical accident risk are completely covered by the collision warning and, for example, both stationary and moving objects are detected.”

Ultrasonic sensor for work platforms

At the beginning of January, Bosch launched two variants of the 24V ultrasonic sensor system for near-field monitoring of the work area. The ultrasonic sensors can be used to secure blind spots, e.g. B. a work basket on aerial work platforms.

Although both 24 V systems have identical hardware, there are differences in how the sensor data is processed and therefore in the range of functions of the different versions. While the basic system only measures the distance to a certain obstacle, the high-end solution also has object localization.

Share.

Comments are closed.