Philipp Schillinger
Research Subjects
Philipp Schillinger has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Dimos V. Dimarogonas
3 shared publicationsMathias Bürger
Bosch Center for Artificial Intelligence, Renningen, Germany
2 shared publications- Alberto Romay
Simulation, Systems Optimization and Robotics Group CS Dept. Technische Universität Darmstadt Hochschulstrasse 10, 64289 Darmstadt Hesse Germany
1 shared publication - Alexander Stumpf
TU Darmstadt
1 shared publication - Alexandros Makris
Institute of Computer Science, Foundation for Research and Technology Hellas (ICS-FORTH), N. Plastira 100, Vassilika Vouton, 70013 Heraklion, Greece
1 shared publication Antonis Argyros
1 shared publication
Latest Publications
- Open Access
Diffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations
Ensuring safety and robustness of robot skills is becoming crucial as robots are required to perform increasingly complex and dynamic tasks. The former is essential when performing tasks in cluttered environments, while the latter is relevant to overcome unseen task situations. This paper addresses the challenge of ensuring both safety and robustness in dynamic robot skills learned from demonstrations. Specifically, we build on neural contractive dynamical systems to provide robust extrapolation of the learned skills, while designing a full-body obstacle avoidance strategy that preserves contraction stability via diffeomorphic transforms. This is particularly crucial in complex environments where implicit scene representations, such as Signed Distance Fields (SDFs), are necessary. To this end, our framework called Signed Distance Field Diffeomorphic Transform, leverages SDFs and flow-based diffeomorphisms to achieve contraction-preserving obstacle avoidance. We thoroughly evaluate our framework on synthetic datasets and several real-world robotic tasks in a kitchen environment. Our results show that our approach locally adapts the learned contractive vector field while staying close to the learned dynamics and without introducing highly-curved motion paths, thus outperforming several state-of-the-art methods.
Open AccessDiffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations
Ensuring safety and robustness of robot skills is becoming crucial as robots are required to perform increasingly complex and dynamic tasks. The former is essential when performing tasks in cluttered environments, while the latter is relevant to overcome unseen task situations. This paper addresses the challenge of ensuring both safety and robustness in dynamic robot skills learned from demonstrations. Specifically, we build on neural contractive dynamical systems to provide robust extrapolation of the learned skills, while designing a full-body obstacle avoidance strategy that preserves contraction stability via diffeomorphic transforms. This is particularly crucial in complex environments where implicit scene representations, such as Signed Distance Fields (SDFs), are necessary. To this end, our framework called Signed Distance Field Diffeomorphic Transform, leverages SDFs and flow-based diffeomorphisms to achieve contraction-preserving obstacle avoidance. We thoroughly evaluate our framework on synthetic datasets and several real-world robotic tasks in a kitchen environment. Our results show that our approach locally adapts the learned contractive vector field while staying close to the learned dynamics and without introducing highly-curved motion paths, thus outperforming several state-of-the-art methods.
- Open Access
Flexible Behavior Trees: In search of the mythical HFSMBTH for Collaborative Autonomy in Robotics
In recent years, the model of computation known as Behavior Trees (BT), first developed in the video game industry, has become more popular in the robotics community for defining discrete behavior switching. BTs are threatening to supplant the venerable Hierarchical Finite State Machine (HFSM) model. In this paper we contrast BT and HFSM, pointing out some potential issues with the BT form, and advocate for a hybrid model of computation that uses both BT and HFSM in ways that leverage their individual strengths. The work introduces a new open-source package for ROS 2 that extends the Flexible Behavior Engine (FlexBE) to enable interaction with BT-based behaviors within a HFSM in a way that supports collaborative autonomy. Simulation and hardware demonstrations illustrate the concepts.
Open AccessFlexible Behavior Trees: In search of the mythical HFSMBTH for Collaborative Autonomy in Robotics
In recent years, the model of computation known as Behavior Trees (BT), first developed in the video game industry, has become more popular in the robotics community for defining discrete behavior switching. BTs are threatening to supplant the venerable Hierarchical Finite State Machine (HFSM) model. In this paper we contrast BT and HFSM, pointing out some potential issues with the BT form, and advocate for a hybrid model of computation that uses both BT and HFSM in ways that leverage their individual strengths. The work introduces a new open-source package for ROS 2 that extends the Flexible Behavior Engine (FlexBE) to enable interaction with BT-based behaviors within a HFSM in a way that supports collaborative autonomy. Simulation and hardware demonstrations illustrate the concepts.
- 1 November 2021
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 145
Adaptive heterogeneous multi-robot collaboration from formal task specifications
- 1 November 2021
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 145
Adaptive heterogeneous multi-robot collaboration from formal task specifications
- Top Cited Papers
- 23 May 2018
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 37 (7) , 818-838
Simultaneous task allocation and planning for temporal logic goals in heterogeneous multi-robot systems
This paper describes a framework for automatically generating optimal action-level behavior for a team of robots based on temporal logic mission specifications under resource constraints. The proposed approach optimally allocates separable tasks to available robots, without requiring a priori an explicit representation of the tasks or the computation of all task execution costs. Instead, we propose an approach for identifying sub-tasks in an automaton representation of the mission specification and for simultaneously allocating the tasks and planning their execution. The proposed framework avoids the need to compute a combinatorial number of possible assignment costs, where each computation itself requires solving a complex planning problem. This can improve computational efficiency compared with classical assignment solutions, in particular for on-demand missions where task costs are unknown in advance. We demonstrate the applicability of the approach with multiple robots in an existing office environment and evaluate its performance in several case study scenarios.
- 23 May 2018
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 37 (7) , 818-838
Top Cited PapersSimultaneous task allocation and planning for temporal logic goals in heterogeneous multi-robot systems
This paper describes a framework for automatically generating optimal action-level behavior for a team of robots based on temporal logic mission specifications under resource constraints. The proposed approach optimally allocates separable tasks to available robots, without requiring a priori an explicit representation of the tasks or the computation of all task execution costs. Instead, we propose an approach for identifying sub-tasks in an automaton representation of the mission specification and for simultaneously allocating the tasks and planning their execution. The proposed framework avoids the need to compute a combinatorial number of possible assignment costs, where each computation itself requires solving a complex planning problem. This can improve computational efficiency compared with classical assignment solutions, in particular for on-demand missions where task costs are unknown in advance. We demonstrate the applicability of the approach with multiple robots in an existing office environment and evaluate its performance in several case study scenarios.
- 14 March 2018
- Published by Springer Nature
- p. 253-267
Decomposition of Finite LTL Specifications for Efficient Multi-agent Planning
- 14 March 2018
- Published by Springer Nature
- p. 253-267
Decomposition of Finite LTL Specifications for Efficient Multi-agent Planning
- 8 September 2016
- Published by Wiley in Journal of Field Robotics
- Vol. 34 (2) , 333-358
Collaborative Autonomy between High‐level Behaviors and Human Operators for Remote Manipulation Tasks using Different Humanoid Robots
- 8 September 2016
- Published by Wiley in Journal of Field Robotics
- Vol. 34 (2) , 333-358
Collaborative Autonomy between High‐level Behaviors and Human Operators for Remote Manipulation Tasks using Different Humanoid Robots