Search

In nature, animals with exceptional locomotion abilities, such as cougars, often possess asymmetric fore and hind legs. This observation inspired us: could optimizing the leg length of quadruped robots endow them with similar locomotive capabilities? In this paper, we propose an approach that co-optimizes the mechanical structure and control policy to boost the locomotive prowess of quadruped robots. Specifically, we introduce a novel pretraining-finetuning framework, which not only guarantees optimal control strategies for each mechanical candidate but also ensures time efficiency. Additionally, we have devised an innovative training method for our pretraining network, integrating spatial domain randomization with regularization methods, markedly improving the network's generalizability. Our experimental results indicate that the proposed pretraining-finetuning framework significantly enhances the overall co-design performance with less time consumption. Moreover, the co-design strategy substantially exceeds the conventional method of independently optimizing control strategies, further improving the robot's locomotive performance and providing an innovative approach to enhancing the extreme parkour capabilities of quadruped robots.

Self-assessment rules play an essential role in safe and effective real-world robotic applications, which verify the feasibility of the selected action before actual execution. But how to utilize the self-assessment results to re-choose actions remains a challenge. Previous methods eliminate the selected action evaluated as failed by the self-assessment rules, and re-choose one with the next-highest affordance~(i.e. process-of-elimination strategy [1]), which ignores the dependency between the self-assessment results and the remaining untried actions. However, this dependency is important since the previous failures might help trim the remaining over-estimated actions. In this paper, we set to investigate this dependency by learning a failure-aware policy. We propose two architectures for the failure-aware policy by representing the self-assessment results of previous failures as the variable state, and leveraging recurrent neural networks to implicitly memorize the previous failures. Experiments conducted on three tasks demonstrate that our method can achieve better performances with higher task success rates by less trials. Moreover, when the actions are correlated, learning a failure-aware policy can achieve better performance than the process-of-elimination strategy.

With the increasing computing power, using data-driven approaches to co-design a robot's morphology and controller has become a promising way. However, most existing data-driven methods require training the controller for each morphology to calculate fitness, which is time-consuming. In contrast, the dual-network framework utilizes data collected by individual networks under a specific morphology to train a population network that provides a surrogate function for morphology optimization. This approach replaces the traditional evaluation of a diverse set of candidates, thereby speeding up the training. Despite considerable results, the online training of both networks impedes their performance. To address this issue, we propose a concurrent network framework that combines online and offline reinforcement learning (RL) methods. By leveraging the behavior cloning term in a flexible manner, we achieve an effective combination of both networks. We conducted multiple sets of comparative experiments in the simulator and found that the proposed method effectively addresses issues present in the dual-network framework, leading to overall algorithmic performance improvement. Furthermore, we validated the algorithm on a real robot, demonstrating its feasibility in a practical application.

In this paper, we investigate the optimal output tracking problem for linear discrete-time systems with unknown dynamics using reinforcement learning and robust output regulation theory. This output tracking problem only allows to utilize the outputs of the reference system and the controlled system, rather than their states, and differs from most existing tracking results that depend on the state of the system. The optimal tracking problem is formulated into a linear quadratic regulation problem by proposing a family of dynamic discrete-time controllers. Then, it is shown that solving the output tracking problem is equivalent to solving output regulation equations, whose solution, however, requires the knowledge of the complete and accurate system dynamics. To remove such a requirement, an off-policy reinforcement learning algorithm is proposed using only the measured output data along the trajectories of the system and the reference output. By introducing re-expression error and analyzing the rank condition of the parameterization matrix, we ensure the uniqueness of the proposed RL based optimal control via output feedback.

For heterogeneous unmanned systems composed of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), using UAVs serve as eyes to assist UGVs in motion planning is a promising research direction due to the UAVs' vast view scope. However, due to UAVs flight altitude limitations, it may be impossible to observe the global map, and motion planning in the local map is a POMDP (Partially Observable Markov Decision Process) problem. This paper proposes a motion planning algorithm for heterogeneous unmanned system under partial observation from UAV without reconstruction of global maps, which consists of two parts designed for perception and decision-making, respectively. For the perception part, we propose the Grid Map Generation Network (GMGN), which is used to perceive scenes from UAV's perspective and classify the pathways and obstacles. For the decision-making part, we propose the Motion Command Generation Network (MCGN). Due to the addition of memory mechanism, MCGN has planning and reasoning abilities under partial observation from UAVs. We evaluate our proposed algorithm by comparing with baseline algorithms. The results show that our method effectively plans the motion of heterogeneous unmanned systems and achieves a relatively high success rate.

There are many stars that are rotating spheroids in the Universe, and studying them is of very important significance. Since the times of Newton, many astronomers and physicists have researched gravitational properties of stars by considering the moment equations derived from Eulerian hydrodynamic equations. In this paper we study the scattering of spinors of the Dirac equation, and in particular investigate the scattering issue in the limit case of rotating Maclaurin spheroids. Firstly we give the metric of a rotating ellipsoid star, then write the Dirac equation under this metric, and finally derive the scattering solution to the Dirac equation and establish a relation between differential scattering cross-section, $\sigma$, and stellar matter density, $\mu$. It is found that the sensitivity of $\sigma$ to the change in $\mu$ is proportional to the density $\mu$. Because of weak gravitational field and constant mass density, our results are reasonable. The results can be applied to white dwarfs, main sequence stars, red giants, supergiant stars and so on, as long as their gravitational fields are so weak that they can be treated in the Newtonan approximations, and the fluid is assumed to be incompressible. Notice that we take the star's matter density to be its average density and the star is not taken to be compact. Obviously our results cannot be used to study neutron stars and black holes. In particular, our results are suitable for white dwarfs, which have average densities of about $10^{5}-10^{6}$\,g~cm$^{-3}$, corresponding to a range of mass of about $0.21-0.61 M_{\bigodot}$ and a range of radius of about $6000-10000$\,km., Comment: This version exactly corresponds to the published version with 12.pages