Jan Kristof Behrens

Jan Kristof Behrens

Auto-generated profile, based on publicly available information

Jan Kristof Behrens

Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Prague, Czechia

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
LRLukas Rustler
Lukas Rustler
JLJens Lundell
Jens Lundell
JBJan Kristof Behrens
Jan Kristof Behrens
VKVille Kyrki
Ville Kyrki
MHMatej Hoffmann
Matej Hoffmann
Recent advancements in object shape completion have enabled impressive object reconstructions using only visual input. However, due to self-occlusion, the reconstructions have high uncertainty in the occluded object parts, which negatively impacts the performance of downstream robotic tasks such as grasping. In this letter, we propose an active visuo-haptic shape completion method called Act-VH that actively computes where to touch the objects based on the reconstruction uncertainty. Act-VH reconstructs objects from point clouds and calculates the reconstruction uncertainty using IGR, a recent state-of-the-art implicit surface deep neural network. We experimentally evaluate the reconstruction accuracy of Act-VH against five baselines in simulation and in the real world. We also propose a new simulation environment for this purpose. The results show that Act-VH outperforms all baselines and that an uncertainty-driven haptic exploration policy leads to higher reconstruction accuracy than a random policy and a policy driven by Gaussian Process Implicit Surfaces. As a final experiment, we evaluate Act-VH and the best reconstruction baseline on grasping 10 novel objects. The results show that Act-VH reaches a significantly higher grasp success rate than the baseline on all objects. Together, this letter opens up the door for using active visuo-haptic shape completion in more complex cluttered scenes.

11 February 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JBJan Kristof Behrens
Jan Kristof Behrens
KSKarla Stepanova
Karla Stepanova
RLRalph Lange
Ralph Lange
Radoslav ŠkovieraRadoslav Škoviera
Radoslav Škoviera
Multi-modal robot programming with natural language and demonstration is a promising technique for efficient teaching of manipulation tasks in industrial environments. In particular, with modern dual-arm robots designed to quickly take over tasks at typical industrial workbenches, the direct teaching of task sequences hardly utilizes the robots' capabilities. We therefore propose a two-staged approach that combines natural language instructions and demonstration with simultaneous task allocation and motion scheduling based on constraint programming. Instead of providing a task description and demonstrations that are replayed to a large extent, the user describes tasks to be scheduled with all relevant constraints and demonstrates relevant locations relative to workpieces and other objects. With explicitly stated constraints on the partial ordering of tasks, the solver allocates the tasks to the robot arms and schedules them in time while avoiding self-collisions and reducing the makespan in our experiment by 33%. The linguistic concepts of naming and grouping enable systematic reuse of sub-task ensembles. The proposed approach is evaluated with four variants of a gluing use-case from furniture assembly in user studies with ten participants. In these user studies, we observed a speed-up for the task definition of more than six times compared to a textual specification of the planning problems using the Python-based planner API.

20 March 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JSJiri Sedlar
Jiri Sedlar
KSKarla Stepanova
Karla Stepanova
Radoslav ŠkovieraRadoslav Škoviera
Radoslav Škoviera
JBJan K. Behrens
Jan K. Behrens
MTMatus Tuna
Matus Tuna
RBRobert Babuska
Robert Babuska
This paper introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups. The dataset and code are publicly available at http://imitrob.ciirc.cvut.cz/imitrobdataset.php .

20 August 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
PVPetr Vanc
Petr Vanc
GFGiovanni Franzese
Giovanni Franzese
JBJan Kristof Behrens
Jan Kristof Behrens
CSCosimo Della Santina
Cosimo Della Santina
KSKarla Stepanova
Karla Stepanova
RBRobert Babuska
Robert Babuska
Learning from demonstration is a promising approach for teaching robots new skills. However, a central challenge in the execution of acquired skills is the ability to recognize faults and prevent failures. This is essential because demonstrations typically cover only a limited set of scenarios and often only the successful ones. During task execution, unforeseen situations may arise, such as changes in the robot's environment or interaction with human operators. To recognize such situations, this letter focuses on teaching the robot situational awareness by using a camera input and labeling frames as safe or risky. We train a Gaussian Process (GP) regression model fed by a low-dimensional latent space representation of the input images. The model outputs a continuous risk score ranging from zero to one, quantifying the degree of risk at each timestep. This allows for pausing task execution in unsafe situations and directly adding new training data, labeled by the human user. Our experiments on a robotic manipulator show that the proposed method can reliably detect both known and novel faults using only a single example for each new fault. In contrast, a standard multi-layer perceptron (MLP) performs well only on faults it has encountered during training. Our method enables the next generation of cobots to be rapidly deployed with easy-to-set-up, vision-based risk assessment, proactively safeguarding humans and detecting misaligned parts or missing objects before failures occur.

7 July 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
Radoslav ŠkovieraRadoslav Škoviera
Radoslav Škoviera
JBJan Kristof Behrens
Jan Kristof Behrens
KSKarla Stepanova
Karla Stepanova
Specifying robot tasks for low-volume manufacturing scenarios is an open problem. The state-of-the-art robotic systems enable the application of smooth 2 D paths to a 3 D surface but assume that the product engineer provides these paths. We extend this approach with a novel tool-path specification method, which produces smooth paths from noisy demonstrations. The user demonstrates only short patterns and selects a base path relative to an object in front of the robot, along which these patterns should be applied. The representation based on polynomials allows controlling the grade of the smoothness of the resulting tool path. We generate parametrized robot trajectories to meet the use-case-specific constraints and adhere to the robot’s kinodynamic limits. We propose a set of measures to evaluate the quality of the generated curves and corresponding trajectories with respect to executability by a robot. The evaluation in simulation and real-robot experiments showed that the robot could reach up to 15.9% higher constant speed on tool paths generated by our system compared to unprocessed paths.