Recent years have witnessed tremendous progress of intelligent robots brought about by mimicking human intelligence. However, current robots are still far from being able to handle multiple tasks in a dynamic environment as efficiently as humans. To cope with complexity and variability, further progress toward scalability and adaptability are essential for intelligent robots. Here, we report a brain-inspired robotic platform implemented by an unmanned bicycle that exhibits scalability of network scale, quantity and diversity to handle the changing needs of different scenarios. The platform adopts rich coding schemes and a trainable and scalable neural state machine, enabling flexible cooperation of hybrid networks. In addition, an embedded system is developed using a cross-paradigm neuromorphic chip to facilitate the implementation of diverse neural networks in spike or non-spike form. The platform achieved various real-time tasks concurrently in different real-world scenarios, providing a new pathway to enhance robots’ intelligence.

No abstract

Neural state machines (NSMs) with weight tunable synapses and leaky integrate-and-fire neurons can control the workflow according to the input information and current state, which has attracted increasing attention in handling complex control logic for various applications. The emerging memristor crossbar network provides an opportunity to further develop NSMs due to the unique analog properties, high density, low-power consumption, and high scalability. However, memristors exhibit nonideal features, such as variation, nonlinearity, and asymmetry of the conductance update, which may hinder the implementation of memristors in NSMs. In this paper, we investigate the implementation of a memristor in an NSM and demonstrate a fully memristor neural state machine (MNSM). Nonvolatile and volatile memristors are designed to emulate the synaptic and neuronal behaviors in MNSMs, respectively. Through a map search task, the MNSM not only exhibits strong robustness to the substantial nonideal behaviors of memristors but also benefits from these shortcomings, showing a faster convergence in the training process. This work proves the feasibility of applying memristors in NSMs and the great potential of MNSMs in handling complex control logic, which promotes the further development of NSMs for neuromorphic computing systems.

The integration of computer-science-oriented and neuroscience-oriented approaches is believed to be a promising way for the development of artificial general intelligence (AGI). Recently, a hybrid Tianjic chip that integrates both approaches has been reported, providing a general platform to facilitate the research of AGI. The control algorithm for handling various neural networks is the key to this platform; however, it is still primitive. In this work, we propose a hybrid neural state machine (H-NSM) framework that can efficiently cooperate with artificial neural networks and spiking neural networks and control the workflows to accomplish complex tasks. The H-NSM receives input from different types of networks, makes decisions according to the fusing of various information, and sends control signals to the sub-network or actuator. The H-NSM can be trained to adapt to context-aware tasks or sequential tasks, thereby improving system robustness. The training algorithm works correctly even if only 50% of the forced state information is provided. It achieved performance comparable to the optimum algorithm on the Tower of Hanoi task and achieved multiple tasks control on a self-driving bicycle. After only 50 training epochs, the transfer accuracy reaches 100% in the test case. It proves that H-NSM has the potential to advance control logic for hybrid systems, paving the way for designing complex intelligent systems and facilitating the research towards AGI.

Inspired by neuronal diversity in the biological neural system, a plethora of studies proposed to design novel types of artificial neurons and introduce neuronal diversity into artificial neural networks. Recently proposed quadratic neuron, which replaces the inner-product operation in conventional neurons with a quadratic one, have achieved great success in many essential tasks. Despite the promising results of quadratic neurons, there is still an unresolved issue: Is the superior performance of quadratic networks simply due to the increased parameters or due to the intrinsic expressive capability? Without clarifying this issue, the performance of quadratic networks is always suspicious. Additionally, resolving this issue is reduced to finding killer applications of quadratic networks. In this paper, with theoretical and empirical studies, we show that quadratic networks enjoy parametric efficiency, thereby confirming that the superior performance of quadratic networks is due to the intrinsic expressive capability. This intrinsic expressive ability comes from that quadratic neurons can easily represent nonlinear interaction, while it is hard for conventional neurons. Theoretically, we derive the approximation efficiency of the quadratic network over conventional ones in terms of real space and manifolds. Moreover, from the perspective of the Barron space, we demonstrate that there exists a functional space whose functions can be approximated by quadratic networks in a dimension-free error, but the approximation error of conventional networks is dependent on dimensions. Empirically, experimental results on synthetic data, classic benchmarks, and real-world applications show that quadratic models broadly enjoy parametric efficiency, and the gain of efficiency depends on the task. We have shared our code in https://github.com/asdvfghg/quadratic efficiency.