Lunar rock investigation and tri-aspect characterization of lunar farside regolith by a digital twin.

Yutu-2 rover conducted an exciting expedition on the 41st lunar day to investigate a fin-shaped rock at Longji site (45.44°S, 177.56°E) by extending its locomotion margin on perilous peaks. The varied locomotion encountered, especially multi-form wheel slippage, during the journey to the target rock, established unique conditions for a fin-grained lunar regolith analysis regarding bearing, shear and lateral properties based on terramechanics. Here, we show a tri-aspect characterization of lunar regolith and infer the rock's origin using a digital twin. We estimate internal friction angle within 21.5°-42.0° and associated cohesion of 520-3154 Pa in the Chang'E-4 operational site. These findings suggest shear characteristics similar to Apollo 12 mission samples but notably higher cohesion compared to regolith investigated on most nearside lunar missions. We estimate external friction angle in lateral properties to be within 8.3°-16.5°, which fills the gaps of the lateral property estimation of the lunar farside regolith and serves as a foundational parameter for subsequent engineering verifications. Our in-situ spectral investigations of the target rock unveil its composition of iron/magnesium-rich low-calcium pyroxene, linking it to the Zhinyu crater (45.34°S, 176.15°E) ejecta. Our results indicate that the combination of in-situ measurements with robotics technology in planetary exploration reveal the possibility of additional source regions contributing to the local materials at the Chang'E-4 site, implying a more complicated geological history in the vicinity.

NN-Based Reinforcement Learning Optimal Control for Inequality-Constrained Nonlinear Discrete-Time Systems With Disturbances.

Based on actor-critic neural networks (NNs), an optimal controller is proposed for solving the constrained control problem of an affine nonlinear discrete-time system with disturbances. The actor NNs provide the control signals and the critic NNs work as the performance indicators of the controller. By converting the original state constraints into new input constraints and state constraints, the penalty functions are introduced into the cost function, and then the constrained optimal control problem is transformed into an unconstrained one. Further, the relationship between the optimal control input and worst-case disturbance is obtained using the Game theory. With Lyapunov stability theory, the control signals are ensured to be uniformly ultimately bounded (UUB). Finally, the effectiveness of the control algorithms is tested through a numeral simulation using a third-order dynamic system.

Learning physical characteristics like animals for legged robots.

Physical characteristics of terrains, such as softness and friction, provide essential information for legged robots to avoid non-geometric obstacles, like mires and slippery stones, in the wild. The perception of such characteristics often relies on tactile perception and vision prediction. Although tactile perception is more accurate, it is limited to close-range use; by contrast, establishing a supervised or self-supervised contactless prediction system using computer vision requires adequate labeled data and lacks the ability to adapt to the dynamic environment. In this paper, we simulate the behavior of animals and propose an unsupervised learning framework for legged robots to learn the physical characteristics of terrains, which is the first report to manage it online, incrementally and with the ability to solve cognitive conflicts. The proposed scheme allows robots to interact with the environment and adjust their cognition in real time, therefore endowing robots with the adaptation ability. Indoor and outdoor experiments on a hexapod robot are carried out to show that the robot can extract tactile and visual features of terrains to create cognitive networks independently; an associative layer between visual and tactile features is created during the robot's exploration; with the layer, the robot can autonomously generate a physical segmentation model of terrains and solve cognitive conflicts in an ever-changing environment, facilitating its safe navigation.