Improving the adaptability of small-sized quadruped robots has been a longstanding challenge in robotics. However, the weak whole-body coordination in existing small-sized quadruped robots limits their locomotion in many environments. In this work, we propose a teacher-student online learning framework for agile whole-body control of small-sized quadruped robots with a flexible spine. We first select a simple and effective gait pattern, the diagonal symmetrical sequence, using a dynamics model. Based on the reference motions provided by the gait pattern and combined with privileged information, we train a teacher policy to generate high-quality motion data. After setting the state space to match the actual robot’s state space, we initialize the robot’s initial state using the teacher data and train a student policy. Finally, we deploy the student policy on the SQuRo-Lite, a small-sized quadruped robot with a flexible spine, demonstrating that our approach can achieve stable yet dynamic locomotion for walking and turning. In the variable-spacing slalom experiment, the robot is able to flexibly adjust the motion patterns of its spine and legs based on commands, enabling dynamic changes in its turning radius. This further validates that our approach can achieve agile whole-body control for small-sized quadruped robots. This work helps broaden the application scenarios of small quadruped robots.

In this paper, we propose a system for real-time rat pose estimation based on stereo vision. The system is dedicated to robot-rat interaction research. First, we design a lightweight, high-resolution network (RRKDNet) for keypoint detection of the rat. The network is trained on a dataset of rat images, which are captured by the robotic rat in first-person view. Second, based on the keypoint detection results, the pose of the rat is obtained by stereo vision model calculation and robot coordinate transformation. At last, we complete a real-time simulation experiment to reproduce the pose of the rat and the robotic rat. The system has been subjected to a series of experiments and the results demonstrate that our network performs better in speed and performance than similar networks. Compared to similar networks, our network has about one-third the number of parameters, while the detection rate increases by 45.25% (the detection rate is 71.57%). The inference speed (34.42 FPS with dual model simultaneous inference) is also faster. The validation error is only 13.85 pixels on the homemade dataset, which is lower than all backbones in Deeplabcut (a toolbox more frequently used for rat keypoint detection). Thus, this work is a significant step in the autonomous intelligent interaction between robots and rats.

Legged robots are very promising for use in real-world applications, but their operation in narrow spaces is still challenging. One solution for enhancing their environmental adaptability is to design a small-sized biomimetic robot capable of performing multiple motions. By capturing a decent representation of an actual rat (rattus norvegicus), we developed a small-sized quadruped robotic rat (SQuRo), which includes four limbs and one flexible spine. On the basis of the extracted key movement joints, SQuRo was subtly designed with a relatively elongated slim body (aspect ratio: 3.42) and smaller weight (220 g) compared with quadruped robots of the same scale. Accordingly, we propose a control framework for multimodal motion planning, and the appropriate control parameters were tuned through optimization with consideration to the stability and actuation limits. The results obtained through a series of experimental tests reveal that SQuRo achieves a superior motion performance compared with existing state-of-the-art small-sized quadruped robots. Remarkably, SQuRo has an extremely small turning radius (0.48 BL) and strong payload capacity (200 g), and it can recover from falls.

In this paper, we propose an automatic robot-rat interaction framework that enables a robotic rat to realize real-time localization, tracking and movement analysis of a laboratory rat. Specifically, we combine an object detector with stereo matching to achieve fast localization of the laboratory rat. Combined with the rat-like motion of the robot, one-step tracking of the rat is achieved, which enables the robot to eliminate last location error in one cycle of visual servo control. When positioning the rat, a unified quantitative description and analysis of rat motion is implemented by using a state vector composed of the centroids of head, body and tail. Preliminary robot-rat interaction tests show that the robot achieved a steady tracking of a fast-moving rat for a duration of 10 minutes. To the best of our knowledge, it is the first time that a rat-sized robot achieves a continuous tracking of actual rats by a built-in miniature stereo vision system. Experimental results show that the sequence of state vectors accurately represents the pitch movement of the rat. Thus, this work is a step toward more natural interaction between robots and animals.

For a small-sized biomimetic robot, it is challenging to mimic animal-like motion with high speed and high flexibility. To enable high flexibility, high stability, and high biomimicry degree for the robotic rat, we drew inspirations from three agile rat movements, namely, the pitch, yaw, and U-turn movements. First, we proposed key movement joints (KMJs) to capture a decent representation of the rat with a reduced-order model. By extracting the primary KMJs, we determined the number and distribution of robotic joints for the design of a bioinspired spine mechanism. Second, to meet the demand of high biomimicry degree, we generated an optimal compensation term to minimize the trajectory error introduced by simplifying the model. Moreover, we calculated the optimal minimum motion cycle based on the constraints of equilibrium under extreme conditions to ensure high flexibility without compromising the stability. Finally, the proposed method was successfully verified through simulation and experimental tests with a robotic rat endowed with the bioinspired spine mechanism.