Bipedal robots have achieved remarkable locomotion capabilities through reinforcement learning (RL), yet their real-world deployment remains hindered by the sim-to-real gap—dynamics mismatches between simulation and reality that degrade locomotion performance through behavioral deviations. This work introduces an online behavior adaptation framework that bridges this gap at the behavioral level by dynamically aligning emergent locomotion strategies with simulation-derived objectives. Our method integrates two core innovations: (1) a structured latent space constructed via an augmented Variational Autoencoder (VAE), which quantifies behavioral divergence through domain-invariant representations of locomotion patterns, and (2) a closed-loop adaptation module that maps latent-space deviations to real-time adjustments in low-level controller parameters. By reformulating sim-to-real transfer as a problem of behavioral alignment rather than explicit dynamics matching, the framework enables continuous adaptation to unmodeled dynamics mismatch without requiring system identification or offline retraining. Extensive experimental evaluations demonstrate the effectiveness of the proposed method, highlighting its potential to bridge the behavior gap between simulation and reality.

Mobile manipulation is a crucial problem in various real-world applications. However, existing methods have demonstrated unsatisfactory training efficiency and sparse rewards, requiring complex coordination strategies between the mobile base and arm. In this paper, we propose RM-Planner, a planning method for mobile manipulation tasks in unknown complex environments. By adopting a two-layer hierarchical framework, we utilize a whole-body Model Predictive Control (MPC)-based low-level planner to track subgoals and generate aggressive but safe joint commands throughout the entire manipulation process, while a Reinforcement Learning (RL)based high-level policy directly uses 3D point cloud representations of the environment, guiding the robot to achieve optimal manipulation postures based on current observations and specific task objectives. We conduct extensive simulations and real-world experiments, where RM-planner significantly outperforms state-of-the-art methods. Our code will be released at https://github.com/SYSU-RoboticsLab/RM-Planner.git.

Humanoid robot soccer presents several challenges, particularly in maintaining system stability during aggressive kicking motions while achieving precise ball trajectory control. Current solutions, whether traditional position-based control methods or reinforcement learning (RL) approaches, exhibit significant limitations. Model predictive control (MPC) is a prevalent approach for ordinary quadruped and biped robots. While MPC has demonstrated advantages in legged robots, existing studies often oversimplify the leg swing progress, relying merely on simple trajectory interpolation methods. This severely constrains the foot’s environmental interaction capability, hindering tasks such as ball kicking. This study innovatively adapts the spatial-temporal trajectory planning method, which has been successful in drone applications, to bipedal robotic systems. The proposed approach autonomously generates foot trajectories that satisfy constraints on target kicking position, velocity, and acceleration while simultaneously optimizing swing phase duration. Experimental results demonstrate that the optimized trajectories closely mimic human kicking behavior, featuring a backswing motion. Simulation and hardware experiments confirm the algorithm’s efficiency, with trajectory planning times under 1 ms, and its reliability, achieving nearly 100 % task completion accuracy when the soccer goal is within the range of -90° to 90°.

Deep Reinforcement Learning (DRL) controllers for quadrupedal locomotion have demonstrated impressive performance on challenging terrains, allowing robots to execute complex skills such as climbing, running, and jumping. However, existing blind locomotion controllers often struggle to ensure safety and efficient traversal through risky gap terrains, which are typically highly complex, requiring robots to perceive terrain information and select appropriate footholds during locomotion accurately. Meanwhile, existing perception-based controllers still present several practical limitations, including a complex multisensor deployment system and expensive computing resource requirements. This paper proposes a DRL controller named MAstering Risky Gap Terrains (MARG), which integrates terrain maps and proprioception to dynamically adjust the action and enhance the robot's stability in these tasks. During the training phase, our controller accelerates policy optimization by selectively incorporating privileged information (e.g., center of mass, friction coefficients) that are available in simulation but unmeasurable directly in real-world deployments due to sensor limitations. We also designed three foot-related rewards to encourage the robot to explore safe footholds. More importantly, a terrain map generation (TMG) model is proposed to reduce the drift existing in mapping and provide accurate terrain maps using only one LiDAR, providing a foundation for zero-shot transfer of the learned policy. The experimental results indicate that MARG maintains stability in various risky terrain tasks.

Obstacle avoidance for uncrewed aerial vehicles (UAVs) in cluttered environments is significantly challenging. Existing obstacle avoidance for UAVs either focuses on fully static environments or static environments with only a few dynamic objects. In this article, we take the initiative to consider the obstacle avoidance of UAVs in dynamic cluttered environments in which dynamic objects are the dominant objects. This type of environment poses significant challenges to both perception and planning. Multiple dynamic objects possess various motions, making it extremely difficult to estimate and predict their motions using one motion model. The planning must be highly efficient to avoid cluttered dynamic objects. This article proposes fast and adaptive perception and planning for UAVs flying in complex dynamic cluttered environments. A novel and efficient point cloud segmentation strategy is proposed to distinguish static and dynamic objects. To address multiple dynamic objects with different motions, an adaptive estimation method with covariance adaptation is proposed to quickly and accurately predict their motions. Our proposed trajectory optimization algorithm is highly efficient, enabling it to avoid fast objects. Furthermore, an adaptive replanning method is proposed to address the case when the trajectory optimization cannot find a feasible solution, which is common for dynamic cluttered environments. Extensive validations in both simulation and real-world experiments demonstrate the effectiveness of our proposed system for highly dynamic and cluttered environments.

Robust state estimation in challenge situations is still an unsolved problem, especially achieving onboard pose feedback control for aggressive motion. In this paper, we propose robust and real-time event-based visual-inertial odometry (VIO) that incorporates event, image, and inertial measurements. Our approach utilizes line-based event features to provide additional structure and constraint information in human-made scenes, while point-based event and image features complement each other through well-designed feature management. To achieve reliable state estimation, we tightly couple the point-based and line-based visual residuals from the event camera, the point-based visual residual from the standard camera, and the residual from IMU pre-integration using a keyframe-based graph optimization framework. Experiments in the public benchmark datasets show that our method can achieve superior performance compared with the state-of-the-art image-based or event-based VIO. Furthermore, we demonstrate the effectiveness of our pipeline through onboard closed-loop quadrotor aggressive flight and large-scale outdoor experiments. Videos of the evaluations can be found on our website: https://youtu.be/KnWZ4anBMK4.Note to Practitioners—Driven by the need for real-time closed-loop control for drones under aggressive motion and broad illumination environments, many existing VIO systems fail to meet these requirements due to the inherent limitations of standard cameras. Event cameras are bio-inspired sensors that capture pixel-level illumination changes instead of the intensity image with a fixed frame rate, which can provide reliable visual perception during high-speed motions and in high dynamic range scenarios. Therefore, developing state estimation algorithms based on event cameras offers exciting opportunities for robotics. However, adopting event cameras is challenging due to the event streams being composed of asynchronous events which are fundamentally different from the synchronous intensity images. Moreover, event cameras output minimal information or even noise when the relative motion between the camera and the scene is limited, such as in a still state, while standard cameras can provide rich perception information in most scenarios. In this paper, we propose a robust, high-accurate, and real-time optimization-based monocular event-based VIO framework that tightly fuses the event, image, and IMU measurement together. Owing to the well-designed framework and good feature management, our system can provide robust and reliable state estimation in challenging environments. The efficiency of our system is adequate to achieve real-time operation on platforms with limited resources, such as providing onboard pose feedback for quadrotor flights.

Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not trivial because the goal behind the gap is difficult to reach. Second, the error tolerance after Sim2Real is low due to the relatively high speed in comparison to the gap's narrow dimensions. This problem is aggravated by the intractability of collecting real-world data due to the risk of collision damage. In this brief, we propose an end-to-end reinforcement learning framework that solves this task successfully by addressing both problems. To search for dynamically feasible flight trajectories, we use a curriculum learning to guide the agent toward the sparse reward behind the obstacle. To tackle the Sim2Real problem, we propose a Sim2Real framework that can transfer control commands to a real quadrotor without using real flight data. To the best of our knowledge, our brief is the first work that accomplishes successful gap traversing task purely using deep reinforcement learning.

This article presents a novel aerial manipulator (AM) system called the aerial continuum manipulator (AeCoM). The system is comprised of a quadrotor and a tendon-driven continuum robotic manipulator. Compared to current AMs, the AeCoM has the advantages of being lightweight and having high dexterity. The continuum manipulator has two contributions: 1) the development of an IMU-based kinematic model to obtain the precise end-effector pose under external loading and 2) the design of a robust closed-loop kinematic controller that implements fast shape-deformation control and prevents tendon slacking by providing feedback of the configuration space and torque applied on tendons. The article provides a detailed mechanical design of the system and extensive experiments were conducted to validate the system’s performance.

Event cameras are biologically-inspired vision sensors that capture pixel-level illumination changes instead of the intensity image at a fixed frame rate. They offer many advantages over the standard cameras, such as high dynamic range, high temporal resolution (low latency), no motion blur, etc. Therefore, developing state estimation algorithms based on event cameras offers exciting opportunities for autonomous systems and robots. In this paper, we propose monocular visual-inertial odometry for event cameras based on event-corner feature detection and matching with well-designed feature management. More specifically, two different kinds of event representations based on time surface are designed to realize event-corner feature tracking (for front-end incremental estimation) and matching (for loop closure detection). Furthermore, the proposed event representations are used to set mask for detecting the event-corner feature based on the raw event-stream, which ensures the uniformly distributed and spatial consistency characteristic of the event-corner feature. Finally, a tightly coupled, graph-based optimization framework is designed to obtain high-accurate state estimation through fusing pre-integrated IMU measurements and event-corner observations. We validate quantitatively the performance of our system on different resolution event cameras: DAVIS240C (240*180, public dataset, achieve state-of-the-art), DAVIS346 (346*240, real-test), DVXplorer (640*480 real-test). Furthermore, we demonstrate qualitatively the accuracy, robustness, loop closure, and re-localization performance of our framework on different large-scale datasets, and an autonomous quadrotor flight using our Event Visual-inertial Odometry (EVIO) framework. Videos of all the evaluations are presented on the project website.

For conventional aerial manipulators, the robotic arm is rigidly attached to the quadrotor. Consequently, the maneuver of the quadrotor will affect the motion of the robotic arm when it is used for tasks such as inspection. In this paper, we propose a novel aerial manipulator with a self-locking gimbal system which can switch between motion coupled and decoupled mode. Furthermore, a dynamic gravity compensation mechanism is designed, where the location of the battery and the number of teeth are optimized to minimize the weight imbalance of the robotic arm during its motions. To the best of the authors’ knowledge, this is the first aerial manipulator with a motion-decoupled mechanism. Experimental results demonstrate that the proposed manipulator design can significantly improve the performance of the manipulator for general inspection tasks.

Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with high confident tracking results are employed as the keyframes to divide the tracking process into multiple time slots. After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored. Besides, when the current time slot exceeds the maximum frame number, which can be scored, the sample with the lowest score will be discarded. Consequently, the training-set can be efficiently and reliably distilled. Comprehensive tests on two well-known UAV benchmarks prove the effectiveness of our method with real-time speed on single CPU.

Correlation filter (CF)-based methods have demonstrated exceptional performance in visual object tracking for unmanned aerial vehicle (UAV) applications, but suffer from the undesirable boundary effect. To solve this issue, spatially regularized correlation filters (SRDCF) proposes the spatial regularization to penalize filter coefficients, thereby significantly improving the tracking performance. However, the temporal information hidden in the response maps is not considered in SRDCF, which limits the discriminative power and the robustness for accurate tracking. This work proposes a novel approach with dynamic consistency pursued correlation filters, i.e., the CPCF tracker. Specifically, through a correlation operation between adjacent response maps, a practical consistency map is generated to represent the consistency level across frames. By minimizing the difference between the practical and the scheduled ideal consistency map, the consistency level is constrained to maintain temporal smoothness, and rich temporal information contained in response maps is introduced. Besides, a dynamic constraint strategy is proposed to further improve the adaptability of the proposed tracker in complex situations. Comprehensive experiments are conducted on three challenging UAV benchmarks, i.e., UAV123@10FPS, UAVDT, and DTB70. Based on the experimental results, the proposed tracker favorably surpasses the other 25 state-of-the-art trackers with real-time running speed (~43FPS) on a single CPU.

For accomplishing a variety of missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial requirement for UAVs in real applications. In this paper, we proposed such a computationally efficient obstacle avoidance trajectory planner that can be used in unknown cluttered environments. Because of the narrow view field of single depth camera on a UAV, the information of obstacles around is quite limited thus the shortest entire path is difficult to achieve. Therefore we focus on the time cost of the trajectory planner and safety rather than other factors. This planner is mainly composed of a point cloud processor, a waypoint publisher with Heuristic Angular Search(HAS) method and a motion planner with minimum acceleration optimization. Furthermore, we propose several techniques to enhance safety by making the possibility of finding a feasible trajectory as large as possible. The proposed approach is implemented to run onboard in real-time and is tested extensively in simulation and the average control output calculating time of iteration steps is less than 18 ms.

Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clutter background, and other challenging visual factors. Inspired by the cutting-edge attention mechanisms, a novel object tracking framework is proposed to leverage multi-level visual attention. Three primary attention, i.e., contextual attention, dimensional attention, and spatiotemporal attention, are integrated into the training and detection stages of correlation filter-based tracking pipeline. Therefore, the proposed tracker is equipped with robust discriminative power against challenging factors while maintaining high operational efficiency in UAV scenarios. Quantitative and qualitative experiments on two well-known benchmarks with 173 challenging UAV video sequences demonstrate the effectiveness of the proposed framework. The proposed tracking algorithm favorably outperforms 12 state-of-the-art methods, yielding 4.8% relative gain in UAVDT and 8.2% relative gain in UAV123@10fps against the baseline tracker while operating at the speed of ~28 frames per second.

Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects. Several approaches to enlarge search regions have been already proposed in the past years to make up for this shortcoming. However, with excessive background information, more background noises are also introduced and the discriminative filter is prone to learn from the ambiance rather than the object. This situation, along with appearance changes of objects caused by full/partial occlusion, illumination variation, and other reasons has made it more likely to have aberrances in the detection process, which could substantially degrade the credibility of its result. Therefore, in this work, a novel approach to repress the aberrances happening during the detection process is proposed, i.e., aberrance repressed correlation filter (ARCF). By enforcing restriction to the rate of alteration in response maps generated in the detection phase, the ARCF tracker can evidently suppress aberrances and is thus more robust and accurate to track objects. Considerable experiments are conducted on different UAV datasets to perform object tracking from an aerial view, i.e., UAV123, UAVDT, and DTB70, with 243 challenging image sequences containing over 90K frames to verify the performance of the ARCF tracker and it has proven itself to have outperformed other 20 state-of-the-art trackers based on DCF and deep-based frameworks with sufficient speed for real-time applications.

Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As boundary effect severely degrade the quality of object model, it has made it a challenging task for unmanned aerial vehicles (UAV) to perform robust and accurate object following. Traditional hand-crafted features are also not precise and robust enough to describe the object in the viewing point of UAV. In this work, a novel tracker with online enhanced background learning is specifically proposed to tackle boundary effects. Real background samples are densely extracted to learn as well as update correlation filters. Spatial penalization is introduced to offset the noise introduced by exceedingly more background information so that a more accurate appearance model can be established. Meanwhile, convolutional features are extracted to provide a more comprehensive representation of the object. In order to mitigate changes of objects' appearances, multi-frame technique is applied to learn an ideal response map and verify the generated one in each frame. Exhaustive experiments were conducted on 100 challenging UAV image sequences and the proposed tracker has achieved state-of-the-art performance.

This paper presents a novel nonlinear disturbance rejection approach for high precision model-based control of hydraulic robots. While most disturbance rejection approaches make use of observers, we propose a novel adaptive Unscented Kalman Filter to estimate the disturbances in an unbiased minimum-variance sense. The filter is made adaptive such that there is no need to tune the covariance matrix for the disturbance estimation. Furthermore, whereas most model-based control approaches require the linearization of the system dynamics, our method is nonlinear which means that no linearization is required. Through extensive simulations as well as real hardware experiments, we demonstrate that our proposed approach can achieve high precision tracking and can be readily applied to most robotic systems even in the presence of uncertainties and external disturbances. The proposed approach is also compared to existing approaches which demonstrates its superior tracking performance.

We present the first perception-aware model predictive control framework for quadrotors that unifies control and planning with respect to action and perception objectives. Our framework leverages numerical optimization to compute trajectories that satisfy the system dynamics and require control inputs within the limits of the platform. Simultaneously, it optimizes perception objectives for robust and reliable sensing by maximizing the visibility of a point of interest and minimizing its velocity in the image plane. Considering both perception and action objectives for motion planning and control is challenging due to the possible conflicts arising from their respective requirements. For example, for a quadrotor to track a reference trajectory, it needs to rotate to align its thrust with the direction of the desired acceleration. However, the perception objective might require to minimize such rotation to maximize the visibility of a point of interest. A model-based optimization framework, able to consider both perception and action objectives and couple them through the system dynamics, is therefore necessary. Our perception-aware model predictive control framework works in a receding-horizon fashion by iteratively solving a non-linear optimization problem. It is capable of running in real-time, fully onboard our lightweight, small-scale quadrotor using a low-power ARM computer, together with a visual-inertial odometry pipeline. We validate our approach in experiments demonstrating (I) the conflict between perception and action objectives, and (II) improved behavior in extremely challenging lighting conditions.

This paper deals with the active fault-tolerant control for quadrotors which are subjected to a total rotor failure. Previous studies assume that the fault has been detected and isolated and then design a fault-tolerant controller. The present paper proposes a complete active fault-tolerant control system which copes with not only fault detection and isolation but also fault-tolerant control. A novel and efficient fault detection and isolation approach is proposed for the total rotor failure case. An incremental nonlinear dynamic inversion approach is introduced to design the fault-tolerant controller for the quadrotor in the presence of the fault. The complete active fault-tolerant control system enables the quadrotor to achieve any position even after the complete loss of one rotor.