Handling novel printed circuit boards (PCBs) in industrial robotic systems presents persistent challenges in adaptability, precision, and real-time reconfiguration. Traditional systems often require extensive reprogramming and manual intervention when new PCB variants are introduced—resulting in costly downtime and limited flexibility. To address this, we present a novel Behavior Tree (BT)-driven reconfiguration framework that integrates multimodal human-robot interfaces—including vision-based proposals, UI-guided corrections, and kinesthetic demonstrations—into the task execution logic. Unlike existing approaches that treat human input as an external override, our framework embeds these modalities directly into BT control flows and links them to a persistent Knowledge Base for runtime adaptation and learning. Experimental validation on a real robotic workcell demonstrated that full reconfiguration can be completed in under 2.5 minutes, significantly reducing setup time and programming effort. By combining modular BT execution with intuitive human interaction, the proposed system enables scalable, user-adaptive automation for dynamic, high-mix industrial environments.

In a goal-oriented Human Robot Collaborative (HRC) scenario, where the goal is to complete an assembly process, a robust object tracker might not necessarily fulfill its functional role due to the dynamic nature of HRC. Moreover, for an efficient HRC, the functional role of the object tacker should not only be limited to localizing and tracking objects for robotic manipulation. It should also help to determine the current state of the assembly process and verify if the chosen action has been successfully performed and thus to enable an uninterrupted completion of an HRC assembly process. We present a Context Enhanced Framework for Multi Object Tracking, that i) allows uninterrupted completion of an assembly process, ii) improves the overall functional accuracy of the object tracker from 49 percent to 96 percent, and iii) enables the object tracker to handle multiple instance of multiple objects in a HRC setting.

In this paper, a robust, real-time object tracking approach capable of dealing with multiple symmetric and non-symmetric objects in a real-time requirement setting is proposed. The approach relies only on depth data to track multiple objects in a dynamic environment and uses random-forest based learning to deal with problems like object occlusion, motion-blur due to camera motion and clutter. We show that the relation between object motion and the corresponding change in its 3D point cloud data can be learned using only 6 random forests. A framework that unites object pose estimation and object pose tracking to efficiently track multiple objects in 3D space is presented. The approach is robust in tracking objects even in presence of motion blur that causes noisy depth data and is capable of real-time performance with 1.8ms per frame. The experimental evaluations demonstrate the performance of the approach against robustness, accuracy and speed and compare the approach with the state of the art. A publicly available dataset with real-world data is also provided for future benchmarking.

The robotic system integrator's dream of (re)using existing software components and benefiting from a common software framework for service orchestration becomes more and more evident. Current initiatives tend to promote the own framework or class library and do not put a lot of effort into illustrating how to integrate existing functionality from other frameworks. Within joint projects between industry and scientific partners, we typically face the challenge of having several development teams using different techniques, class libraries and open source frameworks. In this context, we want to present our development approach using 4DIAC development tools and explicitly highlight useful extensions added for a smooth integration of heterogeneous components of various frameworks which is shown by examples.