arXiv subjects

Chao Yu

Publications and source records attributed to Chao Yu.

At least 109 records · Page 6Linked to original sources

arXiv2025

Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback

Accurate motion control in the face of disturbances within complex environments remains a major challenge in robotics. Classical model-based approaches often struggle with nonlinearities and unstructured disturbances, while RL-based methods can be fragile when encountering unseen scenarios. In this paper, we propose a novel framework, Neural Internal Model Control, which integrates model-based control with RL-based control to enhance robustness. Our framework streamlines the predictive model by applying Newton-Euler equations for rigid-body dynamics, eliminating the need to capture complex high-dimensional nonlinearities. This internal model combines model-free RL algorithms with predictive error feedback. Such a design enables a closed-loop control structure to enhance the robustness and generalizability of the control system. We demonstrate the effectiveness of our framework on both quadrotors and quadrupedal robots, achieving superior performance compared to state-of-the-art methods. Furthermore, real-world deployment on a quadrotor with rope-suspended payloads highlights the framework's robustness in sim-to-real transfer. Our code is released at https://github.com/thu-uav/NeuralIMC.

cs.RO↗

arXiv2025

What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study

Executing precise and agile flight maneuvers is critical for quadrotors in various applications. Traditional quadrotor control approaches are limited by their reliance on flat trajectories or time-consuming optimization, which restricts their flexibility. Recently, RL-based policy has emerged as a promising alternative due to its ability to directly map observations to actions, reducing the need for detailed system knowledge and actuation constraints. However, a significant challenge remains in bridging the sim-to-real gap, where RL-based policies often experience instability when deployed in real world. In this paper, we investigate key factors for learning robust RL-based control policies that are capable of zero-shot deployment in real-world quadrotors. We identify five critical factors and we develop a PPO-based training framework named SimpleFlight, which integrates these five techniques. We validate the efficacy of SimpleFlight on Crazyflie quadrotor, demonstrating that it achieves more than a 50% reduction in trajectory tracking error compared to state-of-the-art RL baselines. The policy derived by SimpleFlight consistently excels across both smooth polynominal trajectories and challenging infeasible zigzag trajectories on small thrust-to-weight quadrotors. In contrast, baseline methods struggle with high-speed or infeasible trajectories. To support further research and reproducibility, we integrate SimpleFlight into a GPU-based simulator Omnidrones and provide open-source access to the code and model checkpoints. We hope SimpleFlight will offer valuable insights for advancing RL-based quadrotor control. For more details, visit our project website at https://sites.google.com/view/simpleflight/.

cs.RO↗

arXiv2025

Multi-Robot System for Cooperative Exploration in Unknown Environments: A Survey

With the real need of field exploration in large-scale and extreme outdoor environments, cooperative exploration tasks have garnered increasing attention. This paper presents a comprehensive review of multi-robot cooperative exploration systems. First, we review the evolution of robotic exploration and introduce a modular research framework tailored for multi-robot cooperative exploration. Based on this framework, we systematically categorize and summarize key system components. As a foundational module for multi-robot exploration, the localization and mapping module is primarily introduced by focusing on global and relative pose estimation, as well as multi-robot map merging techniques. The cooperative motion module is further divided into learning-based approaches and multi-stage planning, with the latter encompassing target generation, task allocation, and motion planning strategies. Given the communication constraints of real-world environments, we also analyze the communication module, emphasizing how robots exchange information within local communication ranges and under limited transmission capabilities. In addition, we introduce the actual application of multi-robot cooperative exploration systems in DARPA SubT Challenge. Finally, we discuss the challenges and future research directions for multi-robot cooperative exploration in light of real-world trends. This review aims to serve as a valuable reference for researchers and practitioners in the field.

cs.RO↗

arXiv2025

FlightBench: Benchmarking Learning-based Methods for Ego-vision-based Quadrotors Navigation

Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to what extent they truly excel. In this paper, we introduce FlightBench, the first comprehensive benchmark that implements various learning-based methods for ego-vision-based navigation and evaluates them against mainstream optimization-based baselines using a broad set of performance metrics. More importantly, we develop a suite of criteria to assess scenario difficulty and design test cases that span different levels of difficulty based on these criteria. Our results show that while learning-based methods excel in high-speed flight and faster inference, they struggle with challenging scenarios like sharp corners or view occlusion. Analytical experiments validate the correlation between our difficulty criteria and flight performance. Moreover, we verify the trend in flight performance within real-world environments through full-pipeline and hardware-in-the-loop experiments. We hope this benchmark and these criteria will drive future advancements in learning-based navigation for ego-vision quadrotors. Code and documentation are available at https://github.com/thu-uav/FlightBench.

cs.RO↗

arXiv2025

CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models

Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing RL methods -- such as GRPO, REINFORCE++, and RLOO -- often suffer from training instability, where large policy updates and improper clipping can lead to training collapse. To address this issue, we propose Clipped Policy Gradient Optimization with Policy Drift (CPGD), a novel algorithm designed to stabilize policy learning in LMs. CPGD introduces a policy drift constraint based on KL divergence to dynamically regularize policy updates, and leverages a clip mechanism on the logarithm of the ratio to prevent excessive policy updates. We provide theoretical justification for CPGD and demonstrate through empirical analysis that it mitigates the instability observed in prior approaches. Furthermore, we show that CPGD significantly improves performance while maintaining training stability. Our implementation balances theoretical rigor with practical usability, offering a robust alternative for RL in the post-training of LMs. We release our code at https://github.com/ModalMinds/MM-EUREKA.

cs.LG↗

arXiv2025

ICPL: Few-shot In-context Preference Learning via LLMs

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs) have native preference-learning capabilities that allow them to achieve sample-efficient preference learning, addressing this challenge. We propose In-Context Preference Learning (ICPL), which uses in-context learning capabilities of LLMs to reduce human query inefficiency. ICPL uses the task description and basic environment code to create sets of reward functions which are iteratively refined by placing human feedback over videos of the resultant policies into the context of an LLM and then requesting better rewards. We first demonstrate ICPL's effectiveness through a synthetic preference study, providing quantitative evidence that it significantly outperforms baseline preference-based methods with much higher performance and orders of magnitude greater efficiency. We observe that these improvements are not solely coming from LLM grounding in the task but that the quality of the rewards improves over time, indicating preference learning capabilities. Additionally, we perform a series of real human preference-learning trials and observe that ICPL extends beyond synthetic settings and can work effectively with humans-in-the-loop.

cs.AI↗

arXiv2025

mmTracking: Trajectory Tracking for Uplink mmWave Devices with Multi-Path Doppler Difference of Arrival

This paper presents a method, namely mmTracking, for device trajectory tracking in a millimeter wave (mmWave) communication system. In mmTracking, the base station (BS) relies on one line-of-sight (LoS) path and at least two non-line-of-sight (NLoS) paths, which are reflected off two walls respectively, of the uplink channel to track the location of a mobile device versus time. There are at least three radio frequency (RF) chains at the BS. Analog phased array with narrow and adjustable receive beam is connected to each RF chain to capture one signal path, where the angle of arrival (AoA) can be roughly estimated. Due to the carrier frequency offset between the transmitter and the BS, the Doppler frequency of each path could hardly be estimated accurately. Instead, the differences of Doppler frequencies of the three paths can be estimated with much better accuracy. Therefore, a trajectory tracking method based on the Doppler difference and AoA estimations is proposed in mmTracking. Experimental results in a typical indoor environment demonstrate that the average error of transmitter localization and trajectory tracking is less than 20 cm.

eess.SP↗

arXiv2025

Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models

We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a high-level understanding of the semantics of the problem for task planning and a broad range of locomotion and manipulation skills to interact with the environment. Our system builds a high-level reasoning layer with large language models, which generates hybrid discrete-continuous plans as robot code from task descriptions. It comprises multiple LLM agents: a semantic planner that sketches a plan, a parameter calculator that predicts arguments in the plan, a code generator that converts the plan into executable robot code, and a replanner that handles execution failures or human interventions. At the low level, we adopt reinforcement learning to train a set of motion planning and control skills to unleash the flexibility of quadrupeds for rich environment interactions. Our system is tested on long-horizon tasks that are infeasible to complete with one single skill. Simulation and real-world experiments show that it successfully figures out multi-step strategies and demonstrates non-trivial behaviors, including building tools or notifying a human for help. Demos are available on our project page: https://sites.google.com/view/long-horizon-robot.

cs.RO↗

arXiv2025

Human-Robot Cooperative Distribution Coupling for Hamiltonian-Constrained Social Navigation

Navigating in human-filled public spaces is a critical challenge for deploying autonomous robots in real-world environments. This paper introduces NaviDIFF, a novel Hamiltonian-constrained socially-aware navigation framework designed to address the complexities of human-robot interaction and socially-aware path planning. NaviDIFF integrates a port-Hamiltonian framework to model dynamic physical interactions and a diffusion model to manage uncertainty in human-robot cooperation. The framework leverages a spatial-temporal transformer to capture social and temporal dependencies, enabling more accurate spatial-temporal environmental dynamics understanding and port-Hamiltonian physical interactive process construction. Additionally, reinforcement learning from human feedback is employed to fine-tune robot policies, ensuring adaptation to human preferences and social norms. Extensive experiments demonstrate that NaviDIFF outperforms state-of-the-art methods in social navigation tasks, offering improved stability, efficiency, and adaptability.

cs.RO↗

arXiv2025

Differential absorption ozone Lidar with 4H-SiC single-photon detectors

Differential absorption Lidar (DIAL) in the ultraviolet (UV) region is an effective approach for monitoring tropospheric ozone. 4H-SiC single-photon detectors (SPDs) are emergent devices for UV single-photon detection. Here, we demonstrate a 4H-SiC SPD-based ozone DIAL. We design and fabricate the 4H-SiC single-photon avalanche diode with a beveled mesa structure and optimized layer thickness. An active quenching circuit with a quenching time of 1.03 ns is developed to significantly mitigate the afterpulsing effect while enhancing the maximum count rate. After characterization, the SPD exhibits excellent performance with a photon detection efficiency of 16.6% at 266 nm, a dark count rate of 138 kcps, a maximum count rate of 13 Mcps, and an afterpulse probability of 2.7% at room temperature. Then, we apply two 4H-SiC SPDs in an ozone DIAL. The measured ozone concentrations at altitudes of 1-3.5 km agree well with the results of a commercial ozone DIAL. Our work provides an alternative solution for general UV Lidar applications.

physics.optics↗

arXiv2025

Compact and fully functional high-frequency sine wave gating InGaAs/InP single-photon detector module

High-frequency sine wave gating (SWG) InGaAs/InP single-photon detectors (SPDs) are widely used for synchronous near-infrared single-photon detection. For practical use, the size of SPD is one of the most concerning features for system integration. Here we present, to the best of our knowledge, the most compact and fully functional high-frequency SWG InGaAs/InP SPD. We develop a sine wave gating integrated circuit (SWGIC) using system-in-package technology that supports functions including large amplitude sine wave gate generation, coincidence gate generation, phase regulation, amplitude monitoring, and amplitude modulation. Moreover, we design and fabricate a high-performance multi-mode fiber coupled InGaAs/InP single-photon avalanche diode (SPAD) with a compact butterfly package. Furthermore, we implement a monolithically integrated readout circuit (MIRC) to extract the weak avalanche signal from large capacitance response of SWG. Finally, the SWGIC, SPAD, MIRC, and the affiliated circuits are integrated into a single module with a size of 6 cm x 5.7 cm x 1.7 cm. After characterization, the SPD module exhibits a photon detection efficiency of 40%, a dark count rate of 9 kcps, and an afterpulse probability of 4.6% at an operation temperature of 238 K and a hold-off time of 160 ns. Our work provides a practical solution for applications necessitating highly integrated near-infrared single-photon detection.

physics.optics↗

arXiv2025

Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning

This paper tackles the challenging task of maintaining formation among multiple unmanned aerial vehicles (UAVs) while avoiding both static and dynamic obstacles during directed flight. The complexity of the task arises from its multi-objective nature, the large exploration space, and the sim-to-real gap. To address these challenges, we propose a two-stage reinforcement learning (RL) pipeline. In the first stage, we randomly search for a reward function that balances key objectives: directed flight, obstacle avoidance, formation maintenance, and zero-shot policy deployment. The second stage applies this reward function to more complex scenarios and utilizes curriculum learning to accelerate policy training. Additionally, we incorporate an attention-based observation encoder to improve formation maintenance and adaptability to varying obstacle densities. Experimental results in both simulation and real-world environments demonstrate that our method outperforms both planning-based and RL-based baselines in terms of collision-free rates and formation maintenance across static, dynamic, and mixed obstacle scenarios. Ablation studies further confirm the effectiveness of our curriculum learning strategy and attention-based encoder. Animated demonstrations are available at: https://sites.google.com/view/ uav-formation-with-avoidance/.

cs.RO↗

arXiv2025

Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey

Reinforcement Learning (RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well as safety and interpretability concerns. The core reason underlying such dilemmas can be attributed to the fact that most of the work has focused on the computational aspect of value functions or policies using a representational model to describe atomic components of rewards, states and actions etc, thus neglecting the rich high-level declarative domain knowledge of facts, relations and rules that can be either provided a priori or acquired through reasoning over time. Recently, there has been a rapidly growing interest in the use of Knowledge Representation and Reasoning (KRR) methods, usually using logical languages, to enable more abstract representation and efficient learning in RL. In this survey, we provide a preliminary overview on these endeavors that leverage the strengths of KRR to help solving various problems in RL, and discuss the challenging open problems and possible directions for future work in this area.

cs.AI↗

arXiv2024

Rapid Learning in Constrained Minimax Games with Negative Momentum

In this paper, we delve into the utilization of the negative momentum technique in constrained minimax games. From an intuitive mechanical standpoint, we introduce a novel framework for momentum buffer updating, which extends the findings of negative momentum from the unconstrained setting to the constrained setting and provides a universal enhancement to the classic game-solver algorithms. Additionally, we provide theoretical guarantee of convergence for our momentum-augmented algorithms with entropy regularizer. We then extend these algorithms to their extensive-form counterparts. Experimental results on both Normal Form Games (NFGs) and Extensive Form Games (EFGs) demonstrate that our momentum techniques can significantly improve algorithm performance, surpassing both their original versions and the SOTA baselines by a large margin.

cs.LG↗

arXiv2024

An Experimental Study of Passive UAV Tracking with Digital Arrays and Cellular Downlink Signals

Given the prospects of the low-altitude economy (LAE) and the popularity of unmanned aerial vehicles (UAVs), there are increasing demands on monitoring flying objects at low altitude in wide urban areas. In this work, the widely deployed long-term evolution (LTE) base station (BS) is exploited to illuminate UAVs in bistatic trajectory tracking. Specifically, a passive sensing receiver with two digital antenna arrays is proposed and developed to capture both the line-of-sight (LoS) signal and the scattered signal off a target UAV. From their cross ambiguity function, the bistatic range, Doppler shift and angle-of-arrival (AoA) of the target UAV can be detected in a sequence of time slots. In order to address missed detections and false alarms of passive sensing, a multi-target tracking framework is adopted to track the trajectory of the target UAV. It is demonstrated by experiments that the proposed UAV tracking system can achieve a meter-level accuracy.

eess.SP↗

arXiv2024

Hierarchical Multi-agent Meta-Reinforcement Learning for Cross-channel Bidding

Real-time bidding (RTB) plays a pivotal role in online advertising ecosystems. Advertisers employ strategic bidding to optimize their advertising impact while adhering to various financial constraints, such as the return-on-investment (ROI) and cost-per-click (CPC). Primarily focusing on bidding with fixed budget constraints, traditional approaches cannot effectively manage the dynamic budget allocation problem where the goal is to achieve global optimization of bidding performance across multiple channels with a shared budget. In this paper, we propose a hierarchical multi-agent reinforcement learning framework for multi-channel bidding optimization. In this framework, the top-level strategy applies a CPC constrained diffusion model to dynamically allocate budgets among the channels according to their distinct features and complex interdependencies, while the bottom-level strategy adopts a state-action decoupled actor-critic method to address the problem of extrapolation errors in offline learning caused by out-of-distribution actions and a context-based meta-channel knowledge learning method to improve the state representation capability of the policy based on the shared knowledge among different channels. Comprehensive experiments conducted on a large scale real-world industrial dataset from the Meituan ad bidding platform demonstrate that our method achieves a state-of-the-art performance.

cs.AI↗

arXiv2024

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization

Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, multi-agent setting involves a large joint state-action space and coupled behaviors of multiple agents, which bring extra complexity to offline policy optimization. In this work, we revisit the existing offline MARL methods and show that in certain scenarios they can be problematic, leading to uncoordinated behaviors and out-of-distribution (OOD) joint actions. To address these issues, we propose a new offline MARL algorithm, named In-Sample Sequential Policy Optimization (InSPO). InSPO sequentially updates each agent's policy in an in-sample manner, which not only avoids selecting OOD joint actions but also carefully considers teammates' updated policies to enhance coordination. Additionally, by thoroughly exploring low-probability actions in the behavior policy, InSPO can well address the issue of premature convergence to sub-optimal solutions. Theoretically, we prove InSPO guarantees monotonic policy improvement and converges to quantal response equilibrium (QRE). Experimental results demonstrate the effectiveness of our method compared to current state-of-the-art offline MARL methods.

cs.AI↗

arXiv2024

MASP: Scalable GNN-based Planning for Multi-Agent Navigation

We investigate multi-agent navigation tasks, where multiple agents need to reach initially unassigned goals in a limited time. Classical planning-based methods suffer from expensive computation overhead at each step and offer limited expressiveness for complex cooperation strategies. In contrast, reinforcement learning (RL) has recently become a popular approach for addressing this issue. However, RL struggles with low data efficiency and cooperation when directly exploring (nearly) optimal policies in a large exploration space, especially with an increased number of agents(e.g., 10+ agents) or in complex environments (e.g., 3-D simulators). In this paper, we propose the Multi-Agent Scalable Graph-based Planner (MASP), a goal-conditioned hierarchical planner for navigation tasks with a substantial number of agents in the decentralized setting. MASP employs a hierarchical framework to reduce space complexity by decomposing a large exploration space into multiple goal-conditioned subspaces, where a high-level policy assigns agents goals, and a low-level policy navigates agents toward designated goals. For agent cooperation and the adaptation to varying team sizes, we model agents and goals as graphs to better capture their relationship. The high-level policy, the Goal Matcher, leverages a graph-based Self-Encoder and Cross-Encoder to optimize goal assignment by updating the agent and the goal graphs. The low-level policy, the Coordinated Action Executor, introduces the Group Information Fusion to facilitate group division and extract agent relationships across groups, enhancing training efficiency for agent cooperation. The results demonstrate that MASP outperforms RL and planning-based baselines in task efficiency.

cs.LG↗