TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments

In recent years, meta-reinforcement learning (meta-RL) algorithm has been proposed to improve sample efficiency in the field of decision-making and control, enabling agents to learn new knowledge from a small number of samples. However, most research uses the Gaussian distribution to extract task representation, which is poorly adapted to tasks that change in non-stationary environment. To address this problem, we propose a novel meta-reinforcement learning method by leveraging Gaussian mixture model and the transformer network to construct task inference model. The Gaussian mixture model is utilized to extend the task representation and conduct explicit encoding of tasks. Specifically, the classification of tasks is encoded through transformer network to determine the Gaussian component corresponding to the task. By leveraging task labels, the transformer network is trained using supervised learning. We validate our method on MuJoCo benchmarks with non-stationary and multi-task environments. Experimental results demonstrate that the proposed method dramatically improves sample efficiency and accurately recognizes the classification of the tasks, while performing excellently in the environment.

Continuous Gaussian Process Pre-Optimization for Asynchronous Event-Inertial Odometry

Event cameras, as bio-inspired sensors, are asynchronously triggered with high-temporal resolution compared to intensity cameras. Recent work has focused on fusing the event measurements with inertial measurements to enable ego-motion estimation in high-speed and HDR environments. However, existing methods predominantly rely on IMU preintegration designed mainly for synchronous sensors and discrete-time frameworks. In this paper, we propose a continuous-time preintegration method based on the Temporal Gaussian Process (TGP) called GPO. Concretely, we model the preintegration as a time-indexed motion trajectory and leverage an efficient two-step optimization to initialize the precision preintegration pseudo-measurements. Our method realizes a linear and constant time cost for initialization and query, respectively. To further validate the proposal, we leverage the GPO to design an asynchronous event-inertial odometry and compare with other asynchronous fusion schemes within the same odometry system. Experiments conducted on both public and own-collected datasets demonstrate that the proposed GPO offers significant advantages in terms of precision and efficiency, outperforming existing approaches in handling asynchronous sensor fusion.

Asynchronous Event-Inertial Odometry using a Unified Gaussian Process Regression Framework

Recent works have combined monocular event camera and inertial measurement unit to estimate the $SE(3)$ trajectory. However, the asynchronicity of event cameras brings a great challenge to conventional fusion algorithms. In this paper, we present an asynchronous event-inertial odometry under a unified Gaussian Process (GP) regression framework to naturally fuse asynchronous data associations and inertial measurements. A GP latent variable model is leveraged to build data-driven motion prior and acquire the analytical integration capacity. Then, asynchronous event-based feature associations and integral pseudo measurements are tightly coupled using the same GP framework. Subsequently, this fusion estimation problem is solved by underlying factor graph in a sliding-window manner. With consideration of sparsity, those historical states are marginalized orderly. A twin system is also designed for comparison, where the traditional inertial preintegration scheme is embedded in the GP-based framework to replace the GP latent variable model. Evaluations on public event-inertial datasets demonstrate the validity of both systems. Comparison experiments show competitive precision compared to the state-of-the-art synchronous scheme.

Self-reconfiguration Strategies for Space-distributed Spacecraft

This paper proposes a distributed on-orbit spacecraft assembly algorithm, where future spacecraft can assemble modules with different functions on orbit to form a spacecraft structure with specific functions. This form of spacecraft organization has the advantages of reconfigurability, fast mission response and easy maintenance. Reasonable and efficient on-orbit self-reconfiguration algorithms play a crucial role in realizing the benefits of distributed spacecraft. This paper adopts the framework of imitation learning combined with reinforcement learning for strategy learning of module handling order. A robot arm motion algorithm is then designed to execute the handling sequence. We achieve the self-reconfiguration handling task by creating a map on the surface of the module, completing the path point planning of the robotic arm using A*. The joint planning of the robotic arm is then accomplished through forward and reverse kinematics. Finally, the results are presented in Unity3D.

Semantic-Geometric-Physical-Driven Robot Manipulation Skill Transfer via Skill Library and Tactile Representation

Deploying robots in open-world environments involves complex tasks characterized by long sequences and rich interactions, necessitating efficient transfer of robotic skills across diverse and complex scenarios. To address this challenge, we propose a skill library framework based on knowledge graphs, which endows robots with high-level skill awareness and spatial semantic understanding. The framework hierarchically organizes operational knowledge by constructing a "task graph" and a "scene graph" to represent task and scene semantic information, respectively. We introduce a "state graph" to facilitate interaction between high-level task planning and low-level scene information. Furthermore, we propose a hierarchical transfer framework for operational skills. At the task level, the framework integrates contextual learning and chain-of-thought prompting within a four-stage prompt paradigm, leveraging large language models' (LLMs) reasoning and generalization capabilities to achieve task-level subtask sequence transfer. At the motion level, an adaptive trajectory transfer method is developed using the A* algorithm and the skill library, enabling motion-level adaptive trajectory transfer. At the physical level, we introduce an adaptive contour extraction and posture perception method based on tactile perception. This method dynamically obtains high-precision contour and posture information from visual-tactile texture data and adjusts transferred skills, such as contact positions and postures, to ensure effectiveness in new environments. Experimental results validate the effectiveness of the proposed methods. Project website:https://github.com/MingchaoQi/skill_transfer

Neural Predictor for Flight Control with Payload

Aerial robotics for transporting suspended payloads as the form of freely-floating manipulator are growing great interest in recent years. However, the prior information of the payload, such as the mass, is always hard to obtain accurately in practice. The force/torque caused by payload and residual dynamics will introduce unmodeled perturbations to the system, which negatively affects the closed-loop performance. Different from estimation-like methods, this paper proposes Neural Predictor, a learning-based approach to model force/torque caused by payload and residual dynamics as a dynamical system. It results a hybrid model including both the first-principles dynamics and the learned dynamics. This hybrid model is then integrated into a MPC framework to improve closed-loop performance. Effectiveness of proposed framework is verified extensively in both numerical simulations and real-world flight experiments. The results indicate that our approach can capture force/torque caused by payload and residual dynamics accurately, respond quickly to the changes of them and improve the closed-loop performance significantly. In particular, Neural Predictor outperforms a state-of-the-art learning-based estimator and has reduced the force and torque estimation errors by up to 66.15% and 33.33% while using less samples.

An Integrating Comprehensive Trajectory Prediction with Risk Potential Field Method for Autonomous Driving

Due to the uncertainty of traffic participants' intentions, generating safe but not overly cautious behavior in interactive driving scenarios remains a formidable challenge for autonomous driving. In this paper, we address this issue by combining a deep learning-based trajectory prediction model with risk potential field-based motion planning. In order to comprehensively predict the possible future trajectories of other vehicles, we propose a target-region based trajectory prediction model(TRTP) which considers every region a vehicle may arrive in the future. After that, we construct a risk potential field at each future time step based on the prediction results of TRTP, and integrate risk value to the objective function of Model Predictive Contouring Control(MPCC). This enables the uncertainty of other vehicles to be taken into account during the planning process. Balancing between risk and progress along the reference path can achieve both driving safety and efficiency at the same time. We also demonstrate the security and effectiveness performance of our method in the CARLA simulator.

Efficient Continuous-Time Ego-Motion Estimation for Asynchronous Event-based Data Associations

Event cameras are bio-inspired vision sensors that asynchronously measure per-pixel brightness changes. The high temporal resolution and asynchronicity of event cameras offer great potential for estimating the robot motion state. Recent works have adopted the continuous-time ego-motion estimation methods to exploit the inherent nature of event cameras. However, most of the adopted methods have poor real-time performance. To alleviate it, a lightweight Gaussian Process (GP)-based estimation framework is proposed to efficiently estimate motion trajectory from asynchronous event-driven data associations. Concretely, an asynchronous front-end pipeline is designed to adapt event-driven feature trackers and generate feature trajectories from event streams; a parallel dynamic sliding-window back-end is presented within the framework of sparse GP regression on SE(3). Notably, a specially designed state marginalization strategy is employed to ensure the consistency and sparsity of this GP regression. Experiments conducted on synthetic and real-world datasets demonstrate that the proposed method achieves competitive precision and superior robustness compared to the state-of-the-art. Furthermore, the evaluations on three 60 s trajectories show that the proposal outperforms the ISAM2-based method in terms of computational efficiency by 2.64, 4.22, and 11.70 times, respectively.

Learning from Imperfect Demonstrations through Dynamics Evaluation

Standard imitation learning usually assumes that demonstrations are drawn from an optimal policy distribution. However, in real-world scenarios, every human demonstration may exhibit nearly random behavior and collecting high-quality human datasets can be quite costly. This requires imitation learning can learn from imperfect demonstrations to obtain robotic policies that align human intent. Prior work uses confidence scores to extract useful information from imperfect demonstrations, which relies on access to ground truth rewards or active human supervision. In this paper, we propose a dynamics-based method to evaluate the data confidence scores without above efforts. We develop a generalized confidence-based imitation learning framework called Confidence-based Inverse soft-Q Learning (CIQL), which can employ different optimal policy matching methods by simply changing object functions. Experimental results show that our confidence evaluation method can increase the success rate by $40.3\%$ over the original algorithm and $13.5\%$ over the simple noise filtering.

Tactile Active Inference Reinforcement Learning for Efficient Robotic Manipulation Skill Acquisition

Robotic manipulation holds the potential to replace humans in the execution of tedious or dangerous tasks. However, control-based approaches are not suitable due to the difficulty of formally describing open-world manipulation in reality, and the inefficiency of existing learning methods. Thus, applying manipulation in a wide range of scenarios presents significant challenges. In this study, we propose a novel method for skill learning in robotic manipulation called Tactile Active Inference Reinforcement Learning (Tactile-AIRL), aimed at achieving efficient training. To enhance the performance of reinforcement learning (RL), we introduce active inference, which integrates model-based techniques and intrinsic curiosity into the RL process. This integration improves the algorithm's training efficiency and adaptability to sparse rewards. Additionally, we utilize a vision-based tactile sensor to provide detailed perception for manipulation tasks. Finally, we employ a model-based approach to imagine and plan appropriate actions through free energy minimization. Simulation results demonstrate that our method achieves significantly high training efficiency in non-prehensile objects pushing tasks. It enables agents to excel in both dense and sparse reward tasks with just a few interaction episodes, surpassing the SAC baseline. Furthermore, we conduct physical experiments on a gripper screwing task using our method, which showcases the algorithm's rapid learning capability and its potential for practical applications.