SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds

• URL: http://arxiv.org/abs/2409.11195v1
• Date: Tue, 17 Sep 2024 13:53:36 GMT
• Title: SDP: Spiking Diffusion Policy for Robotic Manipulation with Learnable Channel-Wise Membrane Thresholds
• Authors: Zhixing Hou, Maoxu Gao, Hang Yu, Mengyu Yang, Chio-In Ieong,
• Abstract summary: This paper introduces a Spiking Diffusion Policy (SDP) learning method for robotic manipulation. SDP integrates Spiking Neurons and Learnable Channel-wise Membrane Thresholds (LCMT) into the diffusion policy model. We achieve results comparable to those of the ANN counterparts, along with faster convergence speeds than the baseline SNN method.
• Score: 7.4357764462464635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a Spiking Diffusion Policy (SDP) learning method for robotic manipulation by integrating Spiking Neurons and Learnable Channel-wise Membrane Thresholds (LCMT) into the diffusion policy model, thereby enhancing computational efficiency and achieving high performance in evaluated tasks. Specifically, the proposed SDP model employs the U-Net architecture as the backbone for diffusion learning within the Spiking Neural Network (SNN). It strategically places residual connections between the spike convolution operations and the Leaky Integrate-and-Fire (LIF) nodes, thereby preventing disruptions to the spiking states. Additionally, we introduce a temporal encoding block and a temporal decoding block to transform static and dynamic data with timestep $T_S$ into each other, enabling the transmission of data within the SNN in spike format. Furthermore, we propose LCMT to enable the adaptive acquisition of membrane potential thresholds, thereby matching the conditions of varying membrane potentials and firing rates across channels and avoiding the cumbersome process of manually setting and tuning hyperparameters. Evaluating the SDP model on seven distinct tasks with SNN timestep $T_S=4$, we achieve results comparable to those of the ANN counterparts, along with faster convergence speeds than the baseline SNN method. This improvement is accompanied by a reduction of 94.3\% in dynamic energy consumption estimated on 45nm hardware.

Related papers

• Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks [4.142699381024752]
  computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential. We propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density.
  arXiv  Detail & Related papers  (2024-09-08T05:14:22Z)
• Synchronized Stepwise Control of Firing and Learning Thresholds in a Spiking Randomly Connected Neural Network toward Hardware Implementation [0.0]
  We propose hardware-oriented models of intrinsic plasticity (IP) and synaptic plasticity (SP) for spiking randomly connected neural network (RNN) We demonstrate the effectiveness of our model through simulations of temporal data learning and anomaly detection with a spiking RNN using publicly available electrocardiograms.
  arXiv  Detail & Related papers  (2024-04-26T08:26:10Z)
• Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning [51.386945803485084]
  We focus on the task where the agent needs to learn multi-dimensional deterministic policies to control. Most existing spike-based RL methods take the firing rate as the output of SNNs, and convert it to represent continuous action space (i.e., the deterministic policy) through a fully-connected layer. To develop a fully spiking actor network without any floating-point matrix operations, we draw inspiration from the non-spiking interneurons found in insects.
  arXiv  Detail & Related papers  (2024-01-09T07:31:34Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• Deep Learning-Based Synchronization for Uplink NB-IoT [72.86843435313048]
  We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT) The introduced NN architecture leverages residual convolutional networks as well as knowledge of the preamble structure of the 5G New Radio (5G NR) specifications.
  arXiv  Detail & Related papers  (2022-05-22T12:16:43Z)
• Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block [4.081968050250324]
  Spiking neural networks (SNNs) have neuro-temporal information capability, low processing feature, and high biological plausibility. Neuro-MNIST, CIFAR10-S, DVS128 gesture datasets need to aggregate individual events into frames with a higher temporal resolution for event stream classification. We propose a processing-temporal compression method to aggregate individual events into a few time steps of NIST current to reduce the training and inference latency.
  arXiv  Detail & Related papers  (2022-03-18T15:14:13Z)
• Learning to Perform Downlink Channel Estimation in Massive MIMO Systems [72.76968022465469]
  We study downlink (DL) channel estimation in a Massive multiple-input multiple-output (MIMO) system. A common approach is to use the mean value as the estimate, motivated by channel hardening. We propose two novel estimation methods.
  arXiv  Detail & Related papers  (2021-09-06T13:42:32Z)
• Learning to Estimate RIS-Aided mmWave Channels [50.15279409856091]
  We focus on uplink cascaded channel estimation, where known and fixed base station combining and RIS phase control matrices are considered for collecting observations. To boost the estimation performance and reduce the training overhead, the inherent channel sparsity of mmWave channels is leveraged in the deep unfolding method. It is verified that the proposed deep unfolding network architecture can outperform the least squares (LS) method with a relatively smaller training overhead and online computational complexity.
  arXiv  Detail & Related papers  (2021-07-27T06:57:56Z)
• Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels [52.60092598312894]
  We propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. Our proposed solution results in minimal energy consumption and $CO$ emission compared to the considered baselines.
  arXiv  Detail & Related papers  (2021-06-02T07:36:27Z)
• DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks [8.746046482977434]
  DIET-SNN is a low-deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with 5 timesteps (inference latency) on the ImageNet dataset with 12x less compute energy than an equivalent standard ANN.
  arXiv  Detail & Related papers  (2020-08-09T05:07:17Z)

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.