Global localization plays a critical role in many robot applications. LiDAR-based global localization draws the community's focus with its robustness against illumination and seasonal changes. To further improve the localization under large viewpoint differences, we propose RING++ that has roto-translation-invariant representation for place recognition and global convergence for both rotation and translation estimation. With the theoretical guarantee, RING++ is able to address the large viewpoint difference using a lightweight map with sparse scans. In addition, we derive sufficient conditions of feature extractors for the representation preserving the roto-translation invariance, making RING++ a framework applicable to generic multichannel features. To the best of our knowledge, this is the first learning-free framework to address all the subtasks of global localization in the sparse scan map. Validations on real-world datasets show that our approach demonstrates better performance than state-of-the-art learning-free methods and competitive performance with learning-based methods. Finally, we integrate RING++ into a multirobot/session simultaneous localization and mapping system, performing its effectiveness in collaborative applications.

Parkour presents a highly challenging task for legged robots, requiring them to traverse various terrains with agile and smooth locomotion. This necessitates comprehensive understanding of both the robot's own state and the surrounding terrain, despite the inherent unreliability of robot perception and actuation. Current state-of-the-art methods either rely on complex pre-trained high-level terrain reconstruction modules or limit the maximum potential of robot parkour to avoid failure due to inaccurate perception. In this paper, we propose a one-stage end-to-end learning-based parkour framework: Parkour with Implicit-Explicit learning framework for legged robots (PIE) that leverages dual-level implicit-explicit estimation. With this mechanism, even a low-cost quadruped robot equipped with an unreliable egocentric depth camera can achieve exceptional performance on challenging parkour terrains using a relatively simple training process and reward function. While the training process is conducted entirely in simulation, our real-world validation demonstrates successful zero-shot deployment of our framework, showcasing superior parkour performance on harsh terrains.

Locomotion control has long been vital to legged robots. Agile locomotion can be implemented through either model-based controller or reinforcement learning. It is proven that robust controllers can be obtained through model-based methods and learning-based policies have advantages in generalization. This paper proposed a hybrid framework of locomotion controller that combines deep reinforcement learning and simple heuristic policy and assigns them to different activation phases, which provides guidance for adaptive training without producing conflicts between heuristic knowledge and learned policies. The training in simulation follows a step-by-step stochastic curriculum to guarantee success. Domain randomization during training and assistive extra feedback loops on real robot are also adopted to smooth the transition to the real world. Comparison experiments are carried out on both simulated and real Wukong-IV humanoid robots, and the proposed hybrid approach matches the canonical end-to-end approaches with higher rate of success, faster converging speed, and 60% less tracking error in velocity tracking tasks.

With respect to the dynamic target tracking issue in the obstacle environment, this paper provides a collision-free tracking framework combining a modified guidance vector field (GVF) and a disturbance rejection controller. More specifically, two primary improvements are implemented compared with the existing GVF methods. The first improvement involves designing a variable property vector deforming the elliptic integral curves to straight lines pointing to the target point, which prevents the robot from detouring. The other improvement is to construct an adjustable parametric function for blending the attractive field and repulsive field so as to refine the obstacle avoidance performance. Meanwhile, a generalized proportional integral observer (GPIO) based steering controller and a sliding mode based approaching controller are provided to enhance the capability of disturbance rejection. Furthermore, simulation and experimental results demonstrate that the proposed method is efficient in the multi-obstacle environment in terms of tracking the virtual dynamic target and the dynamic quadruped robot target even in the environment with uncertain disturbances.

Inspired by biological systems, we seek to achieve natural dynamics and versatile locomotion for hopping or running robots by installing a series elastic actuator (SEA) in the joints due to its compliant property, passive adaptability and energy storage. However, robots equipped with these actuators have drawbacks in terms of substantial delay and limited bandwidth in their position control, especially when a robot has to choose its foothold while it is running at a demanding speed. To solve these problems, compliance control and adaptive position/torque control are introduced to a hopping- legged robot in this paper. The compliant performance of the robot can be improved through the intrinsic property of an SEA with a torque control algorithm. Combining the kinetics model and stochastic model of a 2-DOF robot, an adaptive position control with Kalman Filtering (KF) is developed to provide rapid convergent state estimation of the load on the robotic end-effector by solving the inverse dynamics. Validating the robustness and effectiveness of the proposed algorithm on our hopping-legged robot Tigger, the experimental results show very good position-tracking and disturbance-rejection, as well as flexible interactions while operating in a complex environment.

The problems of a 7-degree of freedom (DOF) manipulator with rapid and continuous response to uncertain fast-flying objects are addressed: 1) how to effectively solve trajectory planning of the 7-DOF manipulator with multiple criteria; and 2) how to make the 7-DOF manipulator realize the rapid and continuous response to uncertain fast-flying objects. In the proposed approach, based on the trajectory parameterization of the 7-DOF manipulator, a multiobjective teaching-learning-based optimization (MOTLBO) algorithm is adopted to find a close representation of the Pareto optimal set rather than a single solution. As such, an optimal solution can be chosen as digital knowledge information. A new methodology based on a knowledge base representing and learning the operation environment, that is, skill digitization, is presented, which enables the 7-DOF manipulator to realize the rapid and continuous response skill. Simulation and practical testing results of a ping-pong robot validate the feasibility and effectiveness of the proposed approach, in which the online trajectory generation spends only around 1 ms.