Recent advances in legged robotics have highlighted deep reinforcement learning (DRL)-based controllers for their robust adaptability to diverse, unstructured environments. While position-based DRL controllers achieve high tracking accuracy, they offer limited disturbance rejection, which degrades walking stability; torque-based DRL controllers can mitigate this issue but typically require extensive time and trial-and-error to converge. To address these challenges, we propose a Real-Time Motion Generator (RTMG). At each time step, RTMG kinematically synthesizes end-effector trajectories from target translational and angular velocities (yaw rate) and step length, then maps them to joint angles via inverse kinematics to produce imitation data. The RL agent uses this imitation data as a torque bias, which is gradually annealed during training to enable fully autonomous behavior. We further combine the RTMG-generated imitation data with a decaying action priors scheme to ensure both initial stability and motion diversity. The proposed training pipeline, implemented in NVIDIA Isaac Gym with Proximal Policy Optimization (PPO), reliably converges to the target gait pattern. The trained controller is Tensor RT-optimized and runs at 50 Hz on a Jetson Nano; relative to a position-based baseline, torso oscillation is reduced by 24.88% in simulation and 21.24% on hardware, demonstrating the effectiveness of the approach.
For a robot to operate robustly in diverse real-world environments, reliable obstacle perception is essential, which fundamentally requires depth information of the surrounding scene. Monocular depth estimation provides a lightweight alternative to active sensors by predicting depth from a single RGB image. However, due to the absence of sufficient geometric and optical cues, it suffers from inherent depth ambiguity. To address this limitation, we propose R-Depth Net, a monocular absolute depth estimation network that utilizes distance-dependent defocus blur variations and optical flow as complementary depth signals. Furthermore, based on the depth maps generated by R-Depth Net, we design an algorithm for obstacle height estimation and traversability assessment. Experimental results in real-world environments show that the proposed method achieves an average RMSE of 0.30 m (15.7%) and MAE of 0.26 m (15.7%) for distance estimation within the 1.0–3.0 m range. For obstacle height estimation in the range of 0.10–0.20 m, the system achieves an average RMSE of 0.048 m (29.3%) and MAE of 0.040 m (26.4%). Finally, real-time deployment on a quadruped robot demonstrates that the estimated depth and height are sufficiently accurate to support on-board obstacle traversal decision-making.
To ensure that robots can operate reliably in diverse environments, obstacle detection is essential, which requires the acquisition of depth information of the surrounding environment. One approach for obtaining depth information is monocular depth estimation, a technique that predicts scene depth from a single camera input. However, monocular images inherently provide limited cues for depth perception, which restricts estimation accuracy. To address this limitation, we propose R-Depth Net, a monocular depth estimation network that leverages variations in blur intensity with respect to distance and frame-to-frame changes induced by motion as primary cues. Based on the depth maps generated by R-Depth Net, we developed an algorithm that enables a robot to estimate obstacle height and determine whether traversal is feasible. When applied to a quadruped robot platform, the proposed method achieved RMSE 0.30 m and MAE 0.26 m for obstacle distance estimation, and RMSE 0.048 m and MAE 0.040 m for obstacle height estimation. Furthermore, real-world obstacle traversal experiments demonstrated the effectiveness of the proposed monocular camera–based obstacle detection and traversal decision-making framework.