High-precision tiny object alignment remains a common and critical challenge for humanoid robots in real world. To address this problem, this paper proposes a vision-based framework for precisely estimating and controlling the relative position between a handheld tool and a target object for humanoid robots, e.g., a screwdriver tip and a screw head slot. By fusing images from the head and torso cameras on a robot with its head joint angles, the proposed Transformer-based visual servoing method can correct the handheld tool’s positional errors effectively, especially at a close distance. Experiments on M4-M8 screws demonstrate an average convergence error of 0.8-1.3 mm and a success rate of 93%-100%. Through comparative analysis, the results validate that this capability of high-precision tiny object alignment is enabled by the Distance Estimation Transformer architecture and the Multi-Perception-Head mechanism proposed in this paper.

Animals possessing spinal columns often exhibit exceptional agility for highly dynamic locomotion. The spine grants the trunk with increased degrees of freedom, thereby endowing diverse postures. This paper presents the development of a robot STRAY for quadrupedal locomotion, featuring a four-degree-of-freedom spine design. Using trajectory based reinforcement learning techniques, STRAY is able to trot and bound dynamically using its spine. Simulation results reveal the positive roles of spinal movement, such as twisting, extension, retraction and rotation, in helping STRAY realize efficient locomotion. Preliminary results from experiments demonstrate that STRAY can achieve a trotting gait of approximately 0.6 m/s and a bounding gait of 0.7 m/s, with desired velocities of 0.8 m/s and 1.0 m/s, respectively. The results also indicate that reinforcement learning is a feasible way to investigate how the spine should be used in dynamic quadrupedal locomotion and achieve more possibilities in the future.

Torque ripple reduction in quasi-direct drive (QDD) motors is crucial in their robotic applications for dynamic locomotion and dexterous manipulation. In this paper, we present a novel approach for reducing torque ripples of QDD motors, which integrates an angle-based repetitive learning observer (ARLO) and a model predictive control-based field-oriented controller (MPC-FOC). The proposed method successfully improves the torque loop control bandwidth and surpasses conventional proportional-integral (PI) controllers owing to the integrated physical constraints inside MPC. Additionally, the ARLO portion is able to mitigate ripple caused by the inherent cogging torque in brushless motors and also the periodic friction torque from the planetary gearboxes in QDD systems. The effectiveness of the proposed method is demonstrated through both simulation of a single QDD motor and experiments on a two-degree-of-freedom robotic leg, where the performance improvement can be 72.7% in speed tracking and 58.5% in trajectory tracking. The proposed method shows great potential in facilitating smooth motion and precise force control in future robotic applications.

Road extraction from light detection and ranging (LiDAR) point cloud data is crucial for modern urban management, transportation planning, autonomous driving, and so on. However, accurate road extraction is faced with challenges, such as obscuration from foreground elements and interference from similar looking elements. To overcome these challenges, this letter builds upon the classic DeepLabV3+ semantic segmentation model and proposes the CM-DeepLabV3+ model to extract deep context and fuse multistage features for superior road extraction performance. The proposed CM-DeepLabV3+ incorporates a cascade atrous spatial pyramid pooling (C-ASPP) module to enhance the contextual awareness of road features by cascading atrous convolution and incorporating attention mechanisms, an multistage feature fusion (MSFF) module to optimize the feature fusion process and ensure the effective integration of high-level semantic and low-level spatial information, and transfer learning technique to initialize the model weights using an auxiliary dataset and enhance the model’s adaptability and robustness to new scenarios. The experimental results on our customized dataset, which includes diverse urban park scenes across cities in China, demonstrate improved performance of CM-DeepLabV3+ in terms of accuracy, precision, recall, intersection over union (IoU), and$F1$score, validating the effectiveness of this approach.

As we build our legged robots smaller and cheaper, stable and agile control without expensive inertial sensors becomes increasingly important. We seek to enable versatile dynamic behaviors on robots with limited modes of state feedback, specifically proprioceptive-only sensing. This work uses model-based trajectory optimization methods to design open-loop stable motion primitives. We specifically design running gaits for a single-legged planar robot, and can generate motion primitives in under 3 seconds, approaching online-capable speeds. A direct-collocation-formulated optimization generated axial force profiles for the direct-drive robot to achieve desired running speed and apex height. When implemented in hardware, these trajectories produced open-loop stable running. Further, the measured running achieved the desired speed within 10% of the speed specified for the optimization in spite of having no control loop actively measuring or controlling running speed. Additionally, we examine the shape of the optimized force profile and observe features that may be applicable to open-loop stable running in general.

Robots encounter many risks that threaten the success of practical locomotion tasks. Legs break, electrical components overheat, and feet can unexpectedly slip. When all risks cannot be completely avoided, how does a robot decide its best action? We present a method for planning robot motions by reasoning about risk-of-failure probabilities instead of applying cost-penalty functions or inflexible path constraints. This work develops a risk-constrained formulation that can be straightforwardly included in existing motion planning optimizations. The risk constraints scale tractably with many risk sources, and in some cases, only add linear constraints to the optimization problem and are therefore compatible with model-predictive control techniques. We present a toy "Puck World" proof-of-concept example and a practical implementation on a planar monopod robot that runs at 3.2 m/s when permitted to take high-risk maneuvers. We believe this risk approach can be used to optimize robot behaviors under numerous conflicting task pressures and model risk-conscious behaviors in animals.