Abstract Quantifying the predictive uncertainty emerged as a possible solution to common challenges like overconfidence, lack of explainability, and robustness of deep neural networks, albeit one that is often computationally expensive. Many real-world applications are multi-modal in nature and hence benefit from multi-task learning. In autonomous driving or robotics, for example, the joint solution of semantic segmentation and monocular depth estimation has proven to be valuable. To this end, we introduce EMUFormer, a novel student-teacher distillation approach for efficient multi-task uncertainties in the context of joint semantic segmentation and monocular depth estimation. By leveraging the predictive uncertainties of the teacher, EMUFormer achieves new state-of-the-art results on Cityscapes and NYUv2 and additionally estimates reliable predictive uncertainties for both tasks that are comparable or superior to a Deep Ensemble despite being an order of magnitude more efficient to compute. These findings even extend to out-of-domain and domain adaptation scenarios, highlighting EMUFormer’s remarkable reliability.

We provide a generic framework for the hand–eye calibration of vision-guided industrial robots. In contrast to traditional methods, we explicitly model the uncertainty of the robot in a stochastically founded way. Albeit the repeatability of modern industrial robots is high, their absolute accuracy typically is much lower. This uncertainty—especially if not considered—deteriorates the result of the hand–eye calibration. Our proposed framework does not only result in a high accuracy of the computed hand–eye pose but also provides reliable information about the uncertainty of the robot. It further provides corrected robot poses for a convenient and inexpensive robot calibration. Our framework is computationally efficient and generic in several regards. It supports the use of a calibration target as well as self-calibration without the need for known 3-D points. It optionally enables the simultaneous calibration of the interior camera parameters. The framework is also generic with regard to the robot type and, hence, supports antropomorphic as well as selective compliance assembly robot arm (SCARA) robots, for example. Simulated and real experiments show the validity of the proposed methods. An extensive evaluation of our framework on a public dataset shows a considerably higher accuracy than 15 state-of-the-art methods.

We provide a generic framework for the hand– eye calibration of vision-guided industrial robots. In contrast to traditional methods, we explicitly model the uncertainty of the robot in a statistically sound manner. Albeit the precision of modern industrial robots is high, their absolute accuracy typically is much lower. This uncertainty — if not considered — deteriorates the result of the hand–eye calibration. Our proposed framework not only results in a high accuracy of the computed hand–eye pose but also provides reliable information about the uncertainty of the robot. It further provides corrected robot poses for a convenient and inexpensive robot calibration. Our framework is generic in several respects: It supports the use of a calibration target as well as self-calibration without the need for known 3D points. It optionally allows the simultaneous calibration of the interior camera parameters. The framework is also generic with regard to the robot type, and hence supports articulated as well as SCARA robots, for example. Simulated and real experiments show the validity of the proposed methods.