publications

2025

1. 

   Automated Behaviour-Driven Acceptance Testing of Robotic Systems

   Minh Nguyen, Sebastian Wrede, and Nico Hochgeschwender

   In 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025), 2025

   Abs Website

   The specification and validation of robotics applications require bridging the gap between formulating requirements and systematic testing. This often involves manual and error-prone tasks that become more complex as requirements, design, and implementation evolve. To address this challenge systematically, we propose extending behaviour-driven development (BDD) to define and verify acceptance criteria for robotic systems. In this context, we use domain-specific modelling and represent composable BDD models as knowledge graphs for robust querying and manipulation, facilitating the generation of executable testing models. A domain-specific language helps to efficiently specify robotic acceptance criteria. We explore the potential for automated generation and execution of acceptance tests through a software architecture that integrates a BDD framework, Isaac Sim, and model transformations, focusing on acceptance criteria for pick-and-place applications. We tested this architecture with an existing pick-and-place implementation and evaluated the execution results, which shows how this application behaves and fails differently when tested against variations of the agent and environment. This research advances the rigorous and automated evaluation of robotic systems, contributing to their reliability and trustworthiness.

2. 

   Planning Robot Placement for Object Grasping

   Manish Saini, Melvin Paul Jacob, Minh Nguyen, and 1 more author

   In RoboCup 2024: Robot World Cup XXVII, 2025

   Abs DOI

   When performing manipulation-based activities such as picking objects, a mobile robot needs to position its base at a location that supports successful execution. To address this problem, prominent approaches typically rely on grasp poses being provided by a planner for a target object, which are then analysed to identify the best robot placements for achieving each grasp pose. In this paper, we propose instead to first find robot placements that would not result in collision with the environment and from where picking up the object is feasible, then evaluate them to find the best placement candidate. Our approach takes into account the robot’s reachability, as well as RGB-D images and occupancy grid maps of the environment for identifying suitable robot poses. The proposed algorithm is embedded in a service robot application, in which a person points to select the target object for grasping. We evaluate our approach with a series of grasping experiments, against an existing baseline implementation that commands the robot to a fixed navigation goal. The experimental results demonstrate the validity of our approach, which can serve as a baseline for developing and evaluating more advanced techniques in the future.

3. 

   Specification and Execution of Robotic Acceptance Tests for Object Sorting

   Bastian Hunecke, Minh Nguyen, Nico Hochgeschwender, and 1 more author

   In European Robotics Forum 2025, 2025

   Abs DOI

   Ensuring reliable performance in tasks with high variability is an increasingly important task in the engineering process of robotics applications. This paper introduces an extended toolchain leveraging Behaviour-Driven Development to specify acceptance criteria and high-quality simulations to execute acceptance tests. We demonstrate the effectiveness of the testing approach in a dynamic sorting task with objects picked from a moving conveyor using a Franka Panda robot system. The contributions include an extended domain-specific language for specifying acceptance criteria and an implementation for automated testing of sorting scenarios using NVIDIA IsaacSim. We conclude with a discussion on the current state and future work on acceptance testing for robotics.

2023

1. 

   An Analysis of Behaviour-Driven Requirement Specification for Robotic Competitions

   Minh Nguyen, Nico Hochgeschwender, and Sebastian Wrede

   In 2023 IEEE/ACM 5th International Workshop on Robotics Software Engineering (RoSE), May 2023

   Abs DOI

   Recent scientific and technological advances have enabled robotic applications in various challenging domains, which motivates means to better represent and manage the subsequent increase in number and complexity of requirements. We look into rulebooks of robotic competitions and benchmarks as one publicly available source of requirements and acceptance criteria for evaluating robots’ performance. From our analysis, we derive a Feature Model containing common elements that recur in descriptions of different robotic competitions. We argue how these features can be used to express requirements and acceptance criteria for robotic applications, within the context of the Behaviour-Driven Development (BDD) paradigm. This can serve as a mean not only to analyse and manage requirements, but also to introduce automation into verifying and validating requirements in robotics.

2019

1. “Lucy, Take the Noodle Box!”: Domestic Object Manipulation Using Movement Primitives and Whole Body Motion

   Alex Mitrevski, Abhishek Padalkar, Minh Nguyen, and 1 more author

   In RoboCup 2019: Robot World Cup XXIII, May 2019

   Abs DOI

   For robots acting - and failing - in everyday environments, a predictable behaviour representation is important so that it can be utilised for failure analysis, recovery, and subsequent improvement. Learning from demonstration combined with dynamic motion primitives is one commonly used technique for creating models that are easy to analyse and interpret; however, mobile manipulators complicate such models since they need the ability to synchronise arm and base motions for performing purposeful tasks. In this paper, we analyse dynamic motion primitives in the context of a mobile manipulator - a Toyota Human Support Robot (HSR) - and introduce a small extension of dynamic motion primitives that makes it possible to perform whole body motion with a mobile manipulator. We then present an extensive set of experiments in which our robot was grasping various everyday objects in a domestic environment, where a sequence of object detection, pose estimation, and manipulation was required for successfully completing the task. Our experiments demonstrate the feasibility of the proposed whole body motion framework for everyday object manipulation, but also illustrate the necessity for highly adaptive manipulation strategies that make better use of a robot’s perceptual capabilities.