This paper presents an overview of AiDIN-VI, a force-controllable quadruped robot system with incorporated mandatory abilities of speed, efficiency, and mobility for providing real-world services. This paper describes the design methodologies and principles employed to implement these requisite capabilities on a single robot platform; particularly, the torque sensing method, along with the components and modularization method of the torque-controllable actuator unit are elucidated herein. The developed robot platform is equipped with all necessary components, including onboard PCs (for motion generation and vision mapping), a battery, modular actuator units, a wireless network router, and a remote e-stop controller for autonomous and manual locomotion control. The robot is subdivided into joints, legs, and robots, and its performance is experimentally tested. The capability of the robot with regard to joint torque control (± 70 Nm), leg force control (350 N along the z-axis), robot (vertical loading 25 kg, pulling force 200 N) were experimentally verified, and locomotive performances (walk, pace, trot, and jump) on various terrains were executed. A maximum trot gait speed of 1.2 m/s was recorded, along with minimum costs of transport of 1.187 and 1.15 at a speed of 1.0 m/s and under loading conditions, respectively.

In legged locomotion, the contact force between a robot and the ground plays a crucial role in balancing the robot. However, in quadrupedal robots, general whole-body controllers generate feed-forward force commands without considering the actual torque or force feedback. This paper presents a whole-body controller using the actual joint torque measured from a torque sensor, which enables the quadrupedal robot to demonstrate both dynamic locomotion and reaction to external disturbances. We compute external joint torque using the measured joint torque and the robot’s dynamics, and then we transform this to the moment of the center of mass (CoM). Using the computed CoM moment, the moment-based impedance controller distributes a feed-forward force corresponding to the desired moment of the CoM to stabilize the robot’s balance. Furthermore, to recover balance, the CoM motion is generated using capture point-based stepping control and zero moment point trajectory. The proposed whole-body controller was tested on a quadrupedal robot, named AiDIN-VI. Locomotive abilities on uneven terrains and slopes and in the presence of external disturbances are verified through experiments.

Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact with their surroundings. Among the various tasks in robotic grasping, bin-picking is considered one of the most challenging because of the cluttered bin filled with objects. Also, for the next-level automation, they need to handle unseen objects and discriminate target objects and outliers. This letter proposes a novel dataset generation pipeline for suction-grasping in bin-picking tasks. This pipeline consists of a series of methods that progressively transit from a single object evaluation to an entire scene evaluation and lower the dimension of the labels to the image space. We trained a suction prediction FCN (Fully Convolution Network) with our dataset generated from the pipeline and conducted bin-picking experiments. Our large-scale collision-free annotation enables the network to understand the context of a bin-picking task, where collisions between the gripper and the bin or object are a concern, and distinguishing the background is crucial. The results show that our solution excels the existing methods, and the network demonstrates its context-aware grasp on objects with loosely defined RoI (Region of Interest).

Legged robots, especially quadruped robots, are widely used in various environments due to their advantage in overcoming rough terrains. However, falling is inevitable. Therefore, the ability to overcome a falling state is an essential ability for legged robots. In this paper, we propose a method to fully recover a quadruped robot from a fall using a single-neural network model. The neural network model is trained in two steps in simulations using reinforcement learning, and then directly applied to AiDIN-VIII, a quadruped robot with 12 degrees of freedom. Experimental results using the proposed method show that the robot can successfully recover from a fall within 5 s in various postures, even when the robot is completely turned over. In addition, we can see that the robot successfully recovers from a fall caused by a disturbance.

Path planning in obstacle-dense environments is a challenging problem, particularly for robots with asymmetric rectangular footprints. To address this problem, we propose a novel collision-checking approach, called a Rotatable Area, which represents a range of heading angles where the robot can rotate without colliding with obstacles. Based on the relationship between two rotatable areas, we define safe local motion and extend this concept to the RoA-Planner, a path planning framework in SE(2) dense space. We validate our planner through extensive simulations and real-world experiments in complex and narrow environments. The results demonstrate that our method achieves fast planning speed while ensuring safety and robustness, making it suitable for practical applications.

A manipulator mounted on a mobility platform requires a design that simultaneously meets the demands for lightweight, compactness, and energy efficiency. A gravity compensator is an effective solution that mechanically offsets the gravity torque caused by the weight of the manipulator links, enabling the use of low-capacity motors while maintaining performance comparable to conventional systems. However, existing gravity compensators face notable challenges in terms of spatial efficiency and durability. To address these challenges, this study developed the two-DOF simultaneous gravity compensator based on a spring and slider-crank mechanism to compensate for the gravity torque generated by two consecutive pitch joints. Experimental results demonstrated a high torque compensation rate of 71.58% and a power reduction rate of 32.23% across the full range of motion of the two joints, further confirming consistency with theoretical predictions.