Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning

• URL: http://arxiv.org/abs/2509.05356v2
• Date: Tue, 16 Sep 2025 11:40:33 GMT
• Title: Spiking Neural Networks for Continuous Control via End-to-End Model-Based Learning
• Abstract summary: We show that fully spiking architectures can be trained end-to-end to control robotic arms with multiple degrees of freedom in continuous environments.<n>Our predictive-control framework combines Leaky Integrate-and-Fire dynamics with surrogate gradients, jointly optimizing a forward model for dynamics prediction and a policy network for goal-directed action.<n>Results show that SNNs can achieve stable training and accurate torque control, establishing their viability for high-dimensional motor tasks.
• Score: 0.7366393875723448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. Here, we demonstrate that fully spiking architectures can be trained end-to-end to control robotic arms with multiple degrees of freedom in continuous environments. Our predictive-control framework combines Leaky Integrate-and-Fire dynamics with surrogate gradients, jointly optimizing a forward model for dynamics prediction and a policy network for goal-directed action. We evaluate this approach on both a planar 2D reaching task and a simulated 6-DOF Franka Emika Panda robot. Results show that SNNs can achieve stable training and accurate torque control, establishing their viability for high-dimensional motor tasks. An extensive ablation study highlights the role of initialization, learnable time constants, and regularization in shaping training dynamics. We conclude that while stable and effective control can be achieved, recurrent spiking networks remain highly sensitive to hyperparameter settings, underscoring the importance of principled design choices.

Related papers

• Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers [3.953304476953445]
  We present a parallelizable, differentiable reachability framework in JAX for continuous- and discrete-time systems with analytical and NN-based dynamics and controllers.<n>Our framework combines Taylor-model flowpipe construction with CROWN-style linear bound propagation through a unified representation that preserves affine dependencies.<n>Building on this reachability primitive, we develop (i) a certified training method that encourages reachability-friendly dynamics models and controllers, and (ii) a reachability-aware sampling-based MPC scheme with gradient-based refinement.
  arXiv  Detail & Related papers  (2026-05-25T02:04:06Z)
• Learning-Based Dynamics Modeling and Robust Control for Tendon-Driven Continuum Robots [23.655392951446995]
  Tendon-Driven Robots Continuum (TDCRs) pose significant modeling and control challenges due to complex nonlinearities.<n>This paper proposes a differentiable learning framework that integrates high-fidelity dynamics modeling with robust neural control.
  arXiv  Detail & Related papers  (2026-04-28T14:20:44Z)
• Adapting Neural Robot Dynamics on the Fly for Predictive Control [7.805013939786426]
  We introduce an approach for fast adaptation of neural robot dynamic models that combines offline training with efficient online updates.<n>We demonstrate the approach on a real quadrotor robot, achieving robust predictive tracking control in novel operational conditions.
  arXiv  Detail & Related papers  (2026-04-05T09:45:26Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Context-Aware Deep Lagrangian Networks for Model Predictive Control [17.06619330822293]
  In this work, we extend Deep Lagrangian Networks (DeLaN) to make it context-aware.<n>We also combine DeLaN with a residual dynamics model to leverage the fact that a nominal model of the robot is typically available.<n>Our method reduces the end-effector tracking error by 39%, compared to a 21% improvement achieved by a baseline.
  arXiv  Detail & Related papers  (2025-06-18T08:26:30Z)
• Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control [59.65431931190187]
  Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware.<n>Most continuous control algorithms for continuous control are designed for Artificial Neural Networks (ANNs)<n>We show that this mismatch destabilizes SNN training and degrades performance.<n>We propose a novel proxy target framework to bridge the gap between discrete SNNs and continuous-control algorithms.
  arXiv  Detail & Related papers  (2025-05-30T03:08:03Z)
• Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch [72.26822499434446]
  Auto-Train-Once (ATO) is an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures.
  arXiv  Detail & Related papers  (2024-03-21T02:33:37Z)
• ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
  This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling. We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
  arXiv  Detail & Related papers  (2023-02-11T21:07:30Z)
• Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control [46.81433026280051]
  We present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems. Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions.
  arXiv  Detail & Related papers  (2022-10-23T00:45:05Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach [3.569867801312134]
  We consider the problem of training a provably safe Neural Network (NN) controller for uncertain nonlinear dynamical systems. Our approach is to learn a set of NN controllers during the training phase. When the task becomes available at runtime, our framework will carefully select a subset of these NN controllers and compose them to form the final NN controller.
  arXiv  Detail & Related papers  (2021-09-03T00:38:05Z)
• Neural Dynamic Policies for End-to-End Sensorimotor Learning [51.24542903398335]
  The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces. We propose Neural Dynamic Policies (NDPs) that make predictions in trajectory distribution space. NDPs outperform the prior state-of-the-art in terms of either efficiency or performance across several robotic control tasks.
  arXiv  Detail & Related papers  (2020-12-04T18:59:32Z)
• Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework [30.58186749790728]
  We propose a theoretically-justified approach to maintaining safety in the presence of dynamics uncertainty. Our framework guarantees the high-probability satisfaction of all constraints at all times jointly. This theoretical analysis also motivates two regularizers of last-layer meta-learning models that improve online adaptation capabilities.
  arXiv  Detail & Related papers  (2020-08-26T17:39:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.