Searcharxiv⌕ Search

arXiv subjects

Shaoshuai Mou

Publications and source records attributed to Shaoshuai Mou.

At least 19 recordsLinked to original sources

Koopman Model-Based Reinforcement Learning

We propose a Koopman model-based reinforcement learning (K-MBRL) algorithm for controlling nonlinear robotic systems with unknown dynamics. The K-MBRL learns a control policy by minimizing an approximate policy objective that combines the analytical immediate cost with an estimate of the future cost evaluated at the one-step predicted state. To this end, we develop a stochastic Koopman operator-based learning method to approximate the unknown nonlinear dynamics in a linear representation, while a critic function estimates the remaining future cost. This formulation offers two key advantages. First, the linear Koopman dynamics simplify the model-dependent policy gradient computation to a constant matrix product, enabling computationally efficient policy improvement. Second, one-step model propagation mitigates the accumulation of prediction errors associated with long-horizon rollouts while retaining long-term cost information through the critic. The learned policy enables real-time control through feedforward evaluation without online optimization. We establish policy learning convergence guarantees under standard stochastic approximation assumptions. Simulations on HalfCheetah and quadruped four-legged locomotion tasks demonstrate strong sample efficiency and improved performance compared with classical model-free and model-based reinforcement learning baselines. A pendulum swing-up task is used to assess policy gradient approximation accuracy and conduct ablation studies on the learning mechanism and key hyperparameters. The proposed K-MBRL is further validated on a physical quadruped robot performing a challenging sequence of maneuvers: rising to an upright posture supported by two rounded rear feet, maintaining balance during bipedal walking, and safely returning to the ground, as shown in Fig.1.

cs.RO↗

Decentralized Bi-Level Optimization for Cooperative Orbital Transportation of a Rigid Payload

The rapid growth of the space economy, alongside increasing orbital congestion and debris, is driving demand for reliable on-orbit transportation of large and non-cooperative objects. Performing such transportation with a swarm of small spacecraft distributes risk and removes the single point of failure inherent to monolithic architectures, but requires solving a non-convex trajectory optimization coupling every agent's cone-constrained thrust to the payload's rotational dynamics. Existing approaches span decentralized control laws with asymptotic guarantees but limited constraint enforcement, and centralized and partially centralized planners that reintroduce a single point of failure. In this work, we present a decentralized bi-level framework driven by exact gradients: the problem is split into an inner convex thrust allocation and an outer search over payload torque trajectories. This decomposition yields fuel-efficient solutions quickly, without requiring full NLP convergence, and at short timescales its performance scales with the number of agents. Theoretical convergence guarantees are established, and the method is validated through extensive Monte Carlo simulation, including closed-loop recovery from in-flight faults. These properties make the framework well suited to spacecraft swarm applications.

eess.SY↗

Stability Transfer for Autonomous Systems via Higher-Order Taylor-Truncated Lyapunov Certificates

We develop analytical sufficient conditions for certifying the local asymptotic stability of nonlinear autonomous systems based on Lyapunov functions derived from their finite-order Taylor polynomial approximations. This approach translates the stability analysis problem from the original nonlinear dynamics to a more computationally tractable polynomial domain. The derived conditions allow for the explicit calculation of a guaranteed inner approximation of the region of attraction ($\mathrm{ROA}$). We show how sum-of-squares (SOS) programming and grid search can be used to systematically search for polynomial Lyapunov functions that yield a large certified threshold radius and extract a certified invariant set inner approximation of the $\mathrm{ROA}$ of the nonpolynomial original system. The framework is then applied to a control tuning problem: finding reduced-effort Linear Quadratic Regulator (LQR) controllers that ensure that a given initial state of interest belongs to the certified $\mathrm{ROA}$ of the nonpolynomial closed loop system. The effectiveness of the overall methodology is demonstrated using a pendulum with nonlinear damping and a nonlinear control system.

eess.SY↗

Neural Operator Learning for Collision-Aware Trajectory Planning of Spacecraft Swarms

Satellite constellations require orbital transfers that are both fuel efficient and collision avoidant. Yet, the computational cost of optimization methods traditionally used to plan their trajectories scales poorly with both the number of satellites as well as the number of obstacles to avoid, due to the pairwise safety constraints. In this work, we introduce a permutation-equivariant neural operator for trajectory planning of spacecraft swarms. This neural operator maps distributions of spacecraft initial states, target states, and obstacle initial states to trajectories which avoid collision and conserve fuel. This neural operator output is then paired with a batched Gauss-Newton finish to enforce exact orbital dynamics, and further reduce fuel use. The operator is self-supervised, trained without optimal trajectory labels. When trained on ten spacecraft, the proposed method generalized zero-shot to swarms of 1,000 spacecraft and 11,000 obstacles. The generated trajectories matched a per-agent optimal control solver's accuracy while retaining collision avoidance. Operator learning grounded in physics may offer a fast, scalable alternative to trajectory optimization in the increasingly crowded orbits of the future.

cs.LG↗

Trajectory Prediction via Bayesian Intention Inference under Unknown Goals and Kinematics

This work introduces an adaptive Bayesian algorithm for real-time trajectory prediction via intention inference, where a target's intentions and motion characteristics are unknown and subject to change. The method concurrently estimates two critical variables: the target's current intention, modeled as a Markovian latent state, and an intention parameter that describes the target's adherence to a shortest-path policy. By integrating this joint update technique, the proposed algorithm maintains robustness against abrupt intention shifts in trajectory prediction and unknown motion dynamics. A sampling-based trajectory prediction mechanism then exploits these adaptive estimates to generate probabilistic forecasts with quantified uncertainty. We validate the algorithm through numerical experiments: Ablation studies of two cases, and a 500-trial Monte Carlo analysis; Hardware demonstrations on quadrotor and quadrupedal platforms. Experimental results demonstrate that the proposed approach significantly outperforms non-adaptive and partially adaptive methods. The method operates in real time around 547 Hz without requiring training or detailed prior knowledge of target behavior, showcasing its applicability in various robotic systems.

cs.RO↗

Stress-Sharing for Decentralized Fault Repair in Modular Spacecraft

Structural damage in modular spacecraft can disrupt mechanical and communication connectivity, reducing system capability. Existing approaches rely on redundancy or preplanned reconfiguration and do not enable autonomous repair under local information and physical constraints. We model the spacecraft as a lattice-constrained graph and introduce a fully decentralized, asynchronous stress-sharing repair policy inspired by biological wound healing: local distress signals guide surviving modules toward damaged regions to close fragmented gaps, after which each displaced module locally retraces its own motions to recover the pre-damage shape, using only local information and no absolute position sensing. We evaluate the policy in PyBullet rigid-body simulation across structures of up to 160 modules, three fault densities (10, 20, 30%), and random and localized damage. The policy consolidates the surviving modules into a single connected body: even in the most severe case tested, where 30% of modules fail at random, it gathers roughly 80% or more of the surviving modules into one connected component, and this fraction improves with assembly size, making the approach well suited as a swarm-scale repair policy for large modular spacecraft.

cs.RO↗

Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics

This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics. To improve the computational efficiency of classic MPPI while preserving control performance, we replace the nonlinear dynamics used for trajectory propagation with a learned linear deep Koopman operator (DKO) model, enabling faster rollout and more efficient trajectory sampling. The DKO dynamics are learned directly from interaction data, eliminating the need for analytical system models. The resulting controller, termed MPPI-DK, is evaluated in simulation on pendulum balancing and surface vehicle navigation tasks, and validated on hardware through reference-tracking experiments on a quadruped robot. Experimental results demonstrate that MPPI-DK achieves control performance close to MPPI with true dynamics while substantially reducing computational cost, enabling efficient real-time control on robotic platforms.

cs.RO↗

Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales

Deploying robot teams in the real world requires simultaneous adaptation to unseen environments, unknown partners, and varying team sizes, yet existing approaches often address these challenges in isolation under the closed-world assumption of fixed teammates. We formalize this as open adaptive multi-robot teaming and propose a hypergraphic-form game formulation that captures team-level cooperative relationships beyond pairwise interactions, providing a principled foundation for coordination structure inference when team composition changes dynamically within episodes. Unlike graph neural network architectures, this is a game-theoretic construct for modeling strategic interactions and payoff structures among agents. Building on this formulation, we develop the Hypergraphic Open-ended Learning Algorithm (HOLA), which progressively expands partner and environment diversity during training rather than optimizing for fixed configurations. Evaluated on cooperative pursuit with multi-drone and multi-quadruped platforms, HOLA outperforms all baselines across all three adaptability dimensions. Learned policies transfer directly to physical hardware without fine-tuning, with successful deployments on Crazyflie and Zsibot L1 platforms confirming robust real-world coordination in novel environments with unseen teammates.

cs.RO↗

DREAM-Chunk: Reactive Action Chunking with Latent World Model

Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution. However, once an action chunk is committed, its open-loop execution can be brittle under stochastic dynamics, hardware execution errors, and partial observability. We propose DREAM-Chunk, a test-time scaling method that augments chunking-based policies with a lightweight latent world model, without requiring additional policy fine-tuning. At test time, DREAM-Chunk samples multiple candidate action chunks, rolls out their predicted latent futures, and selects actions from the chunk whose predicted state best matches the observed rollout. In this way, DREAM-Chunk uses additional test-time computation to cover multiple plausible stochastic futures and improve reactivity during long-horizon chunk execution. On the Kinetix benchmark, DREAM-Chunk improves robustness under increasing action noise and benefits from larger candidate sample sizes, especially when demonstrations contain corrective behaviors. We further validate DREAM-Chunk on four manipulation tasks across two robot platforms and two VLA policies under various sources of stochasticity. Across simulation and hardware experiments, DREAM-Chunk improves the robustness of action-chunking policies in stochastic dynamics.

cs.RO↗

Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems

This paper presents a model-based reinforcement learning (RL) framework for optimal closed-loop control of nonlinear robotic systems. The proposed approach learns linear lifted dynamics through Koopman operator theory and integrates the resulting model into an actor-critic architecture for policy optimization, where the policy represents a parameterized closed-loop controller. To reduce computational cost and mitigate model rollout errors, policy gradients are estimated using one-step predictions of the learned dynamics rather than multi-step propagation. This leads to an online mini-batch policy gradient framework that enables policy improvement from streamed interaction data. The proposed framework is evaluated on several simulated nonlinear control benchmarks and two real-world hardware platforms, including a Kinova Gen3 robotic arm and a Unitree Go1 quadruped. Experimental results demonstrate improved sample efficiency over model-free RL baselines, superior control performance relative to model-based RL baselines, and control performance comparable to classical model-based methods that rely on exact system dynamics.

cs.RO↗

Online Intention Prediction via Control-Informed Learning

This paper presents an online intention prediction framework for estimating the goal state of autonomous systems in real time, even when intention is time-varying, and system dynamics or objectives include unknown parameters. The problem is formulated as an inverse optimal control / inverse reinforcement learning task, with the intention treated as a parameter in the objective. A shifting horizon strategy discounts outdated information, while online control-informed learning enables efficient gradient computation and online parameter updates. Simulations under varying noise levels and hardware experiments on a quadrotor drone demonstrate that the proposed approach achieves accurate, adaptive intention prediction in complex environments.

cs.RO↗

Distributed Koopman Learning using Partial Trajectories for Control

This paper proposes a distributed data-driven framework for dynamics learning, termed distributed deep Koopman learning using partial trajectories (DDKL-PT). In this framework, each agent in a multi-agent system is assigned a partial trajectory offline and locally approximates the unknown dynamics using a deep neural network within the Koopman operator framework. By exchanging local estimated dynamics rather than training data, agents achieve consensus on a global dynamics model without sharing their private training trajectories. Simulation studies on a surface vehicle demonstrate that DDKL-PT achieves consensus on the learned dynamics, and each agent attains reasonably small approximation errors on the testing dataset. Furthermore, a model predictive control scheme is developed by integrating the learned Koopman dynamics with known kinematic relations. Results on a reference-tracking task indicate that the distributedly learned dynamics are sufficiently accurate for model-based optimal control.

eess.SY↗

Safe Online Control-Informed Learning

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an extended Kalman filter to incrementally update system parameters in real time, enabling robust and data-efficient adaptation under uncertainty. A softplus barrier function enforces constraint satisfaction during learning and control while eliminating the dependence on high-quality initial guesses. Theoretical analysis establishes convergence and safety guarantees, and the framework's effectiveness is demonstrated on cart-pole and robot-arm systems.

eess.SY↗

Optimal Control of Nonlinear Systems with Unknown Dynamics

This paper presents a data-driven method to find a closed-loop optimal controller, which minimizes a specified infinite-horizon cost function for systems with unknown dynamics. Suppose the closed-loop optimal controller can be parameterized by a given class of functions, hereafter referred to as the policy. The proposed method introduces a novel gradient estimation framework, which approximates the gradient of the cost function with respect to the policy parameters via integrating the Koopman operator with the classical concept of actor-critic. This enables the policy parameters to be tuned iteratively using gradient descent to achieve an optimal controller, leveraging the linearity of the Koopman operator. The convergence analysis of the proposed framework is provided. The control performance of the proposed method is evaluated through simulations compared with classical optimal control methods that usually assume the dynamics are known.

cs.LG↗

Performance Index Shaping for Closed-loop Optimal Control

The design of the performance index, also referred to as cost or reward shaping, is central to both optimal control and reinforcement learning, as it directly determines the behaviors, trade-offs, and objectives that the resulting control laws seek to achieve. A commonly used approach for this inference task in recent years is differentiable trajectory optimization, which allows gradients to be computed with respect to cost parameters by differentiating through an optimal control solver. However, this method often requires repeated solving of the underlying optimal control problem at every iteration, making the method computationally expensive. In this work, assuming known dynamics, we propose a novel framework that analytically links the performance index to the resulting closed-loop optimal control law, thereby transforming a typically bi-level inverse problem into a tractable single-level formulation. Our approach is motivated by the question: given a closed-loop control law that solves an infinite-horizon optimal control problem, how does this law change when the performance index is modified with additional terms? This formulation yields closed-form characterizations for broad classes of systems and performance indices, which not only facilitate interpretation and stability analysis, but also provide insight into the robust stability and input-to-state stable behavior of the resulting nonlinear closed-loop system. Moreover, this analytical perspective enables the generalization of our approach to diverse design objectives, yielding a unifying framework for performance index shaping. Given specific design objectives, we propose a systematic methodology to guide the shaping of the performance index and thereby design the resulting optimal control law.

eess.SY↗

Distributed Koopman Learning with Incomplete Measurements

Koopman operator theory has emerged as a powerful tool for system identification, particularly for approximating nonlinear time-invariant systems (NTIS). This paper considers a network of agents with limited observation capabilities that collaboratively estimate the dynamics of an NTIS. A distributed deep Koopman learning algorithm is developed by integrating Koopman operator theory, deep neural networks, and consensus-based coordination. In the proposed framework, each agent approximates the system dynamics using its partial measurements and lifted states exchanged with its neighbors. This cooperative scheme enables accurate reconstruction of the global dynamics despite the absence of full-state information at individual agents. Simulation results on the Lunar Lander environment from OpenAI Gym demonstrate that the proposed method achieves performance comparable to the centralized deep Koopman learning with full-state access.

eess.SY↗

A Control-Barrier-Function-Based Algorithm for Policy Adaptation in Reinforcement Learning

This paper considers the problem of adapting a predesigned policy, represented by a parameterized function class, from a solution that minimizes a given original cost function to a trade-off solution between minimizing the original objective and an additional cost function. The problem is formulated as a constrained optimization problem, where deviations from the optimal value of the original cost are explicitly constrained. To solve it, we develop a closed-loop system that governs the evolution of the policy parameters, with a closed-loop controller designed to adjust the additional cost gradient to ensure the satisfaction of the constraint. The resulting closed-loop system, termed control-barrier-function-based policy adaptation, exploits the set-invariance property of control barrier functions to guarantee constraint satisfaction. The effectiveness of the proposed method is demonstrated through numerical experiments on the Cartpole and Lunar Lander benchmarks from OpenAI Gym, as well as a quadruped robot, thereby illustrating both its practicality and potential for real-world policy adaptation.

eess.SY↗

Machine Learning-Driven Prediction of Lithium-Ion Battery Power Capability for eVTOL Aircraft

Electric vertical take-off and landing (eVTOL) aircraft have emerged as a promising solution to transform urban transportation. They present a few technical challenges for battery management, a prominent one of which is the prediction of the power capability of their lithium-ion battery systems. The challenge originates from the high C-rate discharging conditions required during eVTOL flights as well as the complexity of lithium-ion batteries' electro-thermal dynamics. This paper, for the first time, formulates a power limit prediction problem for eVTOL which explicitly considers long prediction horizons and the possible occurrence of emergency landings. We then harness machine learning to solve this problem in two intertwined ways. First, we adopt a dynamic model that integrates physics with machine learning to predict a lithium-ion battery's voltage and temperature behaviors with high accuracy. Second, while performing search for the maximum power, we leverage machine learning to predict the remaining discharge time and use the prediction to accelerate the search with fast computation. Our validation results show the effectiveness of the proposed study for eVTOL operations.

eess.SY↗