With an increased demand on productivity and safety in industry, new issues in terms of automated material handling arise. This results in industries not having a homogenous fleet of trucks and driven and driverless trucks are mixed in a dynamic environment. Driven trucks are more flexible than driverless trucks, but are also involved in more accidents. A transition from driven to driverless trucks can increase safety, but also productivity in terms of fewer accidents and more accurate delivery. Hence, reliable and standardized solutions that avoid accidents are important to achieve high productivity and safety. There are two different safety standards for driverless trucks for Europe (EN1525) and U.S. (B56.5–2012) and they have developed differently. In terms of obstacles, they both consider contact with humans. However, a machinery-shaped object has recently been added to the U.S. standard (B56.5–2012). The U.S. standard also considers different materials for different sensors and non-contact sensors. For obstacle detection, the historical contact-sensitive mechanical bumpers as well as the traditional laser scanner used today both have limitations – they do not detect hanging objects. In this work we have identified several thin objects that are of interest in an industrial environment. A test apparatus with a thin structure is introduced for a more uniform way to evaluate sensors. To detect thin obstacles, we used a standard setup of a stereo system and developed this further to a trinocular system (a stereo system with three cameras). We also propose a method to evaluate 3D sensors based on the information from a 2D range sensor. The 3D model is created by measuring the position of a reflector with known position to an object with a known size. The trinocular system, a 3D TOF camera and a Kinect sensor are evaluated with this method. The results showed that the method can be used to evaluate sensors. It also showed that 3D sensor systems have potential to be used on driverless trucks to detect obstacles, initially as a complement to existing safety classed sensors. To improve safety and productivity, there is a need for harmonization of the European and the U.S. safety standards. Furthermore, parallel development of sensor systems and standards is needed to make use of state-of-the-art technology for sensors.
This paper investigates whether a stereo vision system based on points of interest is robust enough to detect obstacles for applications like a mobile robot in an industrial environment and for the visually impaired. Points of interest are extracted with a known method, called KLT. Two algorithms to solve the correspondence problem (Sum of Squared Difference and Variance Normalized Correlation) are used and evaluated as well as a combination of the two. An improvement is made if the two algorithms are combined. The tests show that stereo vision based on points of interest only can be used robustly for obstacle detection if there is enough texture on the obstacle. Otherwise too few points of interest on the object are detected and a reliable estimation of the distance to the object cannot be made.
Human-operated and driverless trucks often collaborate in a mixed work space in industries and warehouses. This is more efficient and flexible than using only one kind of truck. However, since driverless trucks need to give way to trucks, a reliable detection system is required. Several challenges exist in the development of an obstacle detection system in an industrial setting. The first is to select interesting situations and objects. Overhanging objects are often found in industrial environments, e.g. tines on a forklift. Second is choosing a detection system that has the ability to detect those situations. The traditional laser scanner situated two decimetres above the floor does not detect overhanging objects. Third is to ensure that the perception system is reliable. A solution used on trucks today is to mount a 2D laser scanner on the top of the truck and tilt the scanner towards the floor. However, objects at the top of the truck will be detected too late and a collision cannot always be avoided. Our aim is to replace the upper 2D laser scanner with a 3D camera, structural light or time-of-flight (TOF) camera. It is important to maximize the field of view in the desired detection volume. Hence, the placement of the sensor is important. We conducted laboratory experiments to check and compare the various sensors’ capabilities for different colors, used tines and a model of a tine in a controlled industrial environment. We also conducted field experiments in a warehouse. The conclusion is that both the tested structural light and TOF sensors have problems to detect black items that is nonperpendicular to the sensor and at the distance of interest. It is important to optimize the light economy, meaning the illumination power, field of view and exposure time in order to detect as many different objects as possible. Copyright © 2016 by ASTM International
Many vision-based approaches for obstacle detection often state that vertical thin structure is of importance, e.g. poles and trees. However, there are also problem in detecting thin horizontal structures. In an industrial case there are horizontal objects, e.g. cables and fork lifts, and slanting objects, e.g. ladders, that also has to be detected. This paper focuses on the problem to detect thin horizontal structures. We introduce a test apparatus for testing thin objects as a complement for the test pieces for human safety described in the European standard EN 1525 safety of industrial trucks - driverless trucks and their systems. The system uses three cameras, situated as a horizontal pair and a vertical pair, which makes it possible to also detect thin horizontal structures. A sparse disparity map based on edges and a dense disparity map is used to identify problems with a trinocular system. Both methods use the sum of absolute difference to compute the disparity maps. Tests show that the proposed trinocular system detects all objects at the test apparatus. If a sparse or dense method is used is not critical. Further work will implement the algorithm in real time and verify it on a final system in many types of scenery.
Many vision-based approaches for obstacle detection often state that vertical thin structure is of importance, e.g. poles and trees. However, there are also problem in detecting thin horizontal structures. In an industrial case there are horizontal objects, e.g. cables and fork lifts, and slanting objects, e.g. ladders, that also has to be detected. This paper focuses on the problem to detect thin horizontal structures. The system uses three cameras, situated as a horizontal pair and a vertical pair, which makes it possible to also detect thin horizontal structures. A comparison between a sparse disparity map based on edges and a dense disparity map with a column and row filter is made. Both methods use the Sum of Absolute Difference to compute the disparity maps. Special interest has been in scenes with thin horizontal objects. Tests show that the sparse dense method based on the Canny edge detector works better for the environments we have tested.
In this paper we present a new and uniform way of evaluate 3D sensor performance. It is rare that standardized test specifications are used in research on mobile robots. A test rig with objects in the industrial safety standard Safety of industrial trucks - driverless trucks and their systems EN1525 is extended by thin vertical and horizontal objects that represent a fork on a forklift, a ladder and a hanging cable. A comparison of atrinocular stereo vision system, a 3D TOF (Time- Of-Flight) range camera and a Kinect device is made to verify the use of the test rig. All sensors detect the objects in the safety standard EN1525. The Kinect and 3D TOF camera shows reliable results for the objects in the safety standard at distances up to 5 m. The trinocular system is the only sensor in the test that detects the thin structures. The proposed test rig can be used to evaluate sensors to detect thin structures.