Bayesian Deep Predictive Coding for Snake-like Robotic Control in Unknown Terrains

Effectively modeling the spatio-temporal interactions both internally and externally is a challenge in controlling multi-linked snake robots. This paper presents an effective method based on deep predictive coding: SnakeFormer, to address the aforementioned issue. The main contributions include: 1) Deriving a variational free energy function with two innovative regularization terms through Bayesian probabilistic analysis, offering a novel perspective to simulate the interactions between agent and the environment; 2) Introducing an interaction-attention model within a Transformer structure for predicting dynamics, and collaboratively addressing path planning and obstacle avoidance tasks. 3) By incorporating serpenoid embedding and optimizing self-attention computations, the gait stability and motion efficiency are improved. Preliminary experiments and comparative analysis with baseline models fully validate the effectiveness and generalizability of the method.

Authors

• William Ziming Qu
• Jessica Ziyu Qu
• Li Li
• Jie Yang
• Yuanyuan Jia

Keywords

• Analytical models
• Computational modeling
• Snake robots
• Predictive coding
• Predictive models
• Robot sensing systems
• Transformers
• Stability analysis
• Bayes methods
• Collision avoidance
• Robot Control
• Unknown Terrain
• Regularization Term
• Path Planning
• Obstacle Avoidance
• Generality Of The Method
• Neural Network
• Environmental Changes
• Dynamic Model
• Convolutional Neural Network
• Posterior Probability
• Network Training
• Environment Interactions
• Conditional Probability
• Latent Space
• Transformer Model
• Domain Adaptation
• Deep Reinforcement Learning
• Latent State
• Variational Autoencoder
• Probabilistic Graphical Models
• Active Inference
• ReLU Function
• Variational Autoencoder Model
• Sensor Noise
• Transfer Learning
• Real-world Scenarios
• Hidden Layer