We address the challenge of effectively controlling the locomotion of legged robots by incorporating precise frequency and phase characteristics, which is often ignored in locomotion policies that do not account for the periodic nature of walking. We propose a hierarchical architecture that integrates a low-level phase tracker, oscillators, and a high-level phase modulator. This controller allows quadruped robots to walk in a natural manner that is synchronized with external musical rhythms. Our method generates diverse gaits across different frequencies and achieves real-time synchronization with music in the physical world. This research establishes a foundational framework for enabling real-time execution of accurate rhythmic motions in legged robots. The video and code are available at https://music-walker.github.io/.

Learning diverse skills for quadruped robots presents significant challenges, such as mastering complex transitions between different skills and handling tasks of varying difficulty. Existing imitation learning methods, while successful, rely on expensive datasets to reproduce expert behaviors. Inspired by introspective learning, we propose Progressive Adversarial Self-Imitation Skill Transition (PASIST), a novel method that eliminates the need for complete expert datasets. PASIST autonomously explores and selects high-quality trajectories based on predefined target poses instead of demonstrations, leveraging the Generative Adversarial Self-Imitation Learning (GASIL) framework. To further enhance learning, We develop a skill selection module to mitigate mode collapse by balancing the weights of skills with varying levels of difficulty. Through these methods, PASIST is able to reproduce skills corresponding to the target pose while achieving smooth and natural transitions between them. Evaluations on both simulation platforms and the Solo 8 robot confirm the effectiveness of PASIST, offering an efficient alternative to expert-driven learning.

Reinforcement learning (RL) is a fundamental and pivotal algorithm in the advancement of autonomous intelligence, including Embodied Intelligence and Physical Intelligence. The performance of RL directly influences the quality and efficiency of a robot’s decision-making and execution during interactions with its environment. Moreover, the robustness of RL remains a critical challenge that needs to be addressed. A promising approach to enhancing robustness is adversarial reinforcement learning. However, the existing methods primarily focus on perturbations in the state space, while perturbations in the action space have been relatively underexplored. The action space in RL is as crucial as the state space in autonomous intelligence. Furthermore, action-space perturbations provide a more comprehensive evaluation of RL robustness. Therefore, it is necessary and valuable to investigate RL robustness under action-space perturbations for the development of autonomous intelligence. To this end, we propose an adversarial learning framework that employs momentum-based gradient descent to model perturbations in the action space, such as actuator disturbances. Furthermore, we introduce an improved optimization method that integrates historical gradient information into conventional Stochastic Gradient Descent (SGD). This approach enhances training stability and improves perturbation efficiency. The proposed method is evaluated through simulations in the MuJoCo environment and UAV control experiments in GymFC, demonstrating significant improvements in robustness and adaptability under action-space perturbations. Additionally, real-world UAV flight tests are conducted to further validate the effectiveness of the proposed framework. The results confirm that the Sim-to-Real transfer is successful, providing empirical evidence for the applicability of our method in real-world scenarios. This study shows that enhancing RL robustness through action-space perturbations is feasible and effective. More importantly, our findings contribute to the future development of autonomous intelligence, particularly in improving its resilience to uncertainties and dynamic environments.

We address a fundamental challenge in coordinating large-scale 3D drone swarms: how to achieve rapid collective response to environmental stimuli while ensuring group stability and safety. Existing swarm navigation modals often rely on sophisticated individual perception and communication capabilities, which can be computationally expensive and impractical for large swarms. In this paper, we propose the Non-reciprocal Collective Emergent Navigation model (NRCE), a decentralized approach designed for real-world drone flocking in complex environments. Unlike traditional models, our approach leverages localized non-reciprocal interactions, where boundary drones detect environmental stimuli and propagate this information throughout the swarm without directly controlling individual trajectories. Through extensive numerical simulations and physical experiments with up to 28 drones, we demonstrate how this model achieves coordinated collective motion while effectively balancing stability with responsiveness. Our findings reveal two notable insights: (1) intermediate cohesion levels (ωc) optimize collective response—a "Goldilocks zone" where individuals are neither too tightly coupled nor too independent, challenging the conventional wisdom that stronger cohesion always improves coordination; and (2) swarm queue configuration significantly affects optimal interaction parameters, with divergent trends observed between attraction- and repulsion-based coordination mechanisms as layer count increases. These discoveries provide critical design principles for cost-effective, high-density swarm systems while advancing the theoretical understanding of collective dynamics in both artificial and biological systems.

Electric quadruped robots used in outdoor exploration are susceptible to leg-related electrical or mechanical failures. Unexpected joint power loss and joint locking can immediately pose a falling threat. Typically, controllers lack the capability to actively sense the condition of their own joints and take proactive actions. Maintaining the original motion patterns could lead to disastrous consequences, as the controller may produce irrational output within a short period of time, further creating the risk of serious physical injuries. This paper presents a hierarchical fault-tolerant control scheme employing a multi-task training architecture capable of actively perceiving and overcoming two types of leg joint faults. The architecture simultaneously trains three joint task policies for health, power loss, and locking scenarios in parallel, introducing a symmetric reflection initialization technique to ensure rapid and stable gait skill transformations. Experiments demonstrate that the control scheme is robust in unexpected scenarios where a single leg experiences concurrent joint faults in two joints. Furthermore, the policy retains the robot’s planar mobility, enabling rough velocity tracking. Finally, zero-shot Sim2Real transfer is achieved on the real-world SOLO8 robot, countering both electrical and mechanical failures.

Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent approaches invariably focus on designing sophisticated architectures or mechanisms to extract seemingly meaningful representations from subjects and contexts. However, a long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states among different context scenarios. Concretely, the harmful bias is a confounder that misleads existing models to learn spurious correlations based on conventional likelihood estimation, significantly limiting the models' performance. To tackle the issue, this paper provides a causality-based perspective to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a tailored causal graph. Then, we propose a Contextual Causal Intervention Module (CCIM) based on the backdoor adjustment to de-confound the confounder and exploit the true causal effect for model training. CCIM is plug-in and model-agnostic, which improves diverse state-of-the-art approaches by considerable margins. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our CCIM and the significance of causal insight.

The ability to perform efficient trajectory planning is crucial for UAV to carry out tasks autonomously. However, existing research on UAV trajectory planning often employs the cascade process method that involves high-precision maps, real-time positioning and path planning. These methods have limitations such as high computational complexity and time delay, which hinder the efficiency of trajectory planning. End-to-end trajectory planning methods offer a promising solution to this problem. As the core of these end-to-end methods, perception-end plays a decisive role in trajectory planning. But current multimodal fusion of perception is only post-fusion, lacks intermediate feature-level fusion and lacks attention to global visuospatial information. To solve these problems, we propose a new network architecture called FlyTransformer, which fuses the proprioceptive state and visual perception in feature-level for end-to-end trajectory planning. And the key visuospatial information can be attentioned in this architecture. We evaluate our method in forest and cuboid scenarios and their corresponding outdoor scenarios. The results show that FlyTransformer outperforms other baseline algorithms in terms of efficiency and performance.

In modern factories and daily life, the application of heterogeneous robot groups is becoming more and more widespread. However, there are still many areas for improvement in the management and communication of heterogeneous robot swarms, including the need for different connection interfaces for heterogeneous robots and the use of heterogeneous robot action logs to identify possible bottlenecks in the production line or record unplanned behaviors, whether malicious or not. In order to better manage heterogeneous robot swarms, this paper introduces the Heterogeneous Robots Chain (HR-Chain), a blockchain-based solution that can manage different types of robots and prevent unnecessary changes in robot operation logs to help improve production efficiency or other management requirements. HR-Chain is a Tezos-based blockchain project that securely stores robot logs in the blockchain using smart contracts. Finally, this paper conducts experimental research on HR-Chain, the real experimental results show that the robot system based on HR-Chain has better response speed and execution force, showing its potential application prospects in the industrial and consumer fields.

Robust adversarial reinforcement learning is an effective method to train agents to manage uncertain disturbance and modeling errors in real environments. However, for systems that are sensitive to disturbances or those that are difficult to stabilize, it is easier to learn a powerful adversary than establish a stable control policy. An improper strong adversary can destabilize the system, introduce biases in the sampling process, make the learning process unstable, and even reduce the robustness of the policy. In this study, we consider the problem of ensuring system stability during training in the adversarial reinforcement learning architecture. The dissipative principle of robust H-infinity control is extended to the Markov Decision Process, and robust stability constraints are obtained based on L2 gain performance in the reinforcement learning system. Thus, we propose a dissipation-inequation-constraint-based adversarial reinforcement learning architecture. This architecture ensures the stability of the system during training by imposing constraints on the normal and adversarial agents. Theoretically, this architecture can be applied to a large family of deep reinforcement learning algorithms. Results of experiments in MuJoCo and GymFc environments show that our architecture effectively improves the robustness of the controller against environmental changes and adapts to more powerful adversaries. Results of the flight experiments on a real quadcopter indicate that our method can directly deploy the policy trained in the simulation environment to the real environment, and our controller outperforms the PID controller based on hardware-in-the-loop. Both our theoretical and empirical results provide new and critical outlooks on the adversarial reinforcement learning architecture from a rigorous robust control perspective.

Reinforcement learning with adversarial training is currently a key method for improving the robustness of DRL. However, in adversarial training, especially for unstable or disturbance-sensitive systems, the adversary always learns the policy significantly faster than the DRL agent and thus easily generates powerful perturbations. The agent cannot effectively adapt to the overly powerful adversary, which leads to unstable training and even failure to learn the robust policy. In this work, we propose a novel adversarial training method, called Curriculum Adversarial Training, inspired by the idea of curriculum learning. The method dynamically adjusts the strength of the adversary through natural curriculum learning for progressive adversarial training. Thus, the DRL system considers to reasonable learning rules, and the agent faces a suitable learning process. Furthermore, we adopt an advanced action space perturbation method with a most attractive ability as the adversary during training. The proposed method is compared with popular baseline methods through MuJoCo tasks. Experimental results show that our method can improve the robustness of the policy significantly and adapt to uncertain environment effectively.

In this article, a novel vehicle positioning system architecture based on direction-of-arrival (DOA) estimation of incoherently distributed (ID) sources is proposed employing massive multiple-input–multiple-output (MIMO) arrays. Such an architecture with the associated signal model is more consistent with the actual array application and multipath transmission scenarios. First, an end-to-end two-dimensional (2-D) DOA estimation of ID sources utilizing a dual one-dimensional (1-D) convolutional neural network (D1D-CNN) under the deep learning (DL) framework is performed, where the normalized covariance matrix data is used for both offline training and online estimation. Then, the received SNR information is exploited to select a set of DOA estimates provided by multiple collaborative BSs for positioning. Moreover, transfer learning and an attention mechanism are employed to promote its generalization ability and achieve robustness against array perturbations. Simulation results are provided to show that the proposed method outperforms the state-of-the-art methods in terms of computational complexity, positioning accuracy, and robustness against array perturbations.

In massive multiple-input multiple-output (MIMO) systems, accurate direction-of-arrival (DOA) estimation is important for the base station (BS) to perform effective downlink beamforming. So far, there have been few reports on DOA estimation considering gain-phase perturbations in massive MIMO systems. However, gain-phase perturbations indeed exist in practical applications and cannot be ignored. In this paper, an efficient method for two-dimensional (2-D) DOA estimation of incoherently distributed (ID) sources considering array gain-phase perturbations is proposed for massive MIMO systems. Firstly, a shift invariance structure is established in the subspace framework, and a constrained optimization problem is formulated to estimate the nominal azimuth and elevation DOAs as well as gain-phase perturbations with closed-form expressions, under the assumption that some of the BS antennas are well calibrated; secondly, the corresponding angular spreads are obtained with the aid of the estimated gain-phase perturbations. Theoretical analysis and an approximate Cramér-Rao bound are also provided. An improved estimation performance is achieved by the proposed method as demonstrated by numerical simulations.

The paper presents an object detection accelerator featuring a processing-in-memory (PIM) architecture on FPGAs. PIM architectures are well known for their energy efficiency and avoidance of the memory wall. In the accelerator, a PIM unit is developed using BRAM and LUT based counters, which also helps to improve the DSP performance density. The overall architecture consists of 64 PIM units and three memory buffers to store inter-layer results. A shrunk and quantized Tiny-YOLO network is mapped to the PIM accelerator, where DRAM access is fully eliminated during inference. The design achieves a throughput of 201.6 GOPs at 100MHz clock rate and correspondingly, a performance density of 0.57 GOPS/DSP.