
The paper presents an End-User Development (EUD) environment that supports end users in the definition of pick-and-place tasks for collaborative service robots. The proposed environment targets professional service robotics scenarios, where robots operate in close collaboration with human workers in shared workspaces. The environment features a chat-based interface leveraging OpenAI GPT−4.1 that allows the user to define robot tasks in a guided and intuitive manner. The defined robot task is then displayed in a graphic interface based on Google Blockly, which allows the user to check, modify, or extend the task by direct manipulation of puzzle-like components. Finally, a robot program can be generated, and a simulation of its execution can be obtained through a digital twin of the robot. This final step is crucial for validating the defined robot task and identifying any potential issues that may arise during execution, before the actual deployment of the robot program. A user study was conducted to assess the usability, workload, and overall user experience of the proposed environment, providing empirical evidence of its feasibility and effectiveness. This paper contributes to the research field of end-user robot programming by proposing a human-centered artificial intelligence approach that leverages the power of large language models and digital twins. This approach empowers end users, even without programming or robotics expertise, to conceptualize, validate, and refine robot programs through intuitive interfaces. By placing users at the center of the development process, the approach aims to ensure accessible, efficient, and effective programming experiences tailored to their needs.
This research addresses the development of the next-gen humanoid robot collaborative system with a myriad of technologies, ensuring a very smooth and highly accurate interaction. It is one of the few systems capable of maintaining 95
Safety and productivity are two critical aspects of human–robot collaborative (HRC) environments. This paper proposes ranked behavior cloning (RBC), an imitation learning framework that enhances conventional behavior cloning by incorporating a ranking mechanism based on cooperative speed-up (CSU) and jerk-based smoothness. The proposed framework addresses safety at two distinct levels: (1) learned safety-awareness, where the ranking objective penalizes high-jerk, low-productivity demonstrations so the trained policy inherently produces smoother, more cooperative trajectories; and (2) externally enforced safety, implemented as a zone-based Speed and Separation Monitoring (SSM) layer that dynamically adjusts robot speed based on human–robot proximity, inspired by the SSM principles defined in ISO 15066. The proposed RBC model is evaluated on a real-world UR5 collaborative platform across five manipulation tasks, benchmarked against standard behavior cloning (BC) and Maximum Entropy Inverse Reinforcement Learning (MaxEnt-IRL). RBC achieves a positional accuracy of 92.6
Reinforcement learning (RL) has enabled agile legged locomotion; however, transferring these results to a new robot often requires extensive reward redesign and coefficient retuning as the morphology, scale, and actuation constraints change. This study evaluates a gait-parameterized RL formulation for cross-platform locomotion learning without reward retuning. We keep the reward terms and coefficients, network architecture, and PPO hyperparameters fixed and adjust only the platform interface via observation/action mappings and low-level actuation settings. With this setup, we trained separate policies in the simulation on three small quadrupeds (Go1, ANYmal C, and Mini Cheetah), a humanoid (Atlas), and a large-scale hydraulic quadruped (BeTheX-Q), and evaluated their performance across multiple terrains. The results showed stable locomotion across large variations in morphology and physical scale. The learned gait-intent outputs further exhibited systematic scaling and correlation trends with speed, posture, actuation effort, and mechanical cost of transport, thereby providing an interpretable view of embodiment-dependent behaviors under a fixed learning formulation. Finally, we extend the framework to a wheeled-legged hybrid configuration of BeTheX-Q and demonstrate wheel–leg coupled locomotion in both simulation and hardware.
In this paper, we investigate the Minimum Obstacle Displacement Planning problem from a robot motion planning perspective. The problem involves determining a feasible path to a goal location by displacing movable obstacles when no collision-free path initially exists. We show that this problem is computationally challenging and, in particular, NP-hard when obstacles are modeled as polygons in the plane. Besides an exact formulation of the minimum obstacle displacement problem generalizing other problems in the literature, and the associated optimal solution, this paper proposes an approximate solution that is less intensive from a computational standpoint, and differs from the optimal solution by a fraction of the optimal cost, being able to trade-off between path length and amount of obstacle displacements.