Machine Learning Planner for Continuous State Space Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current planning methods for physical systems often rely on discrete state spaces, which can be restrictive and difficult to establish, especially in real-world applications where state spaces are continuous and high-dimensional, limiting their applicability in modeling and solving Markov decision processes.

Innovation Solution

A machine learning device and method that learns an encoder function and transition function from training data to define a Markov decision problem in a continuous latent space, allowing for dynamic programming-based planning without prior knowledge of the state space, enabling planning for physical systems with continuous and high-dimensional observable states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If discrete state spaces are used for planning, then planning can be performed using standard Markov decision processes, but the approach becomes restrictive and difficult to establish for real-world physical systems with continuous and high-dimensional states

Engineering Contradiction:
ImproveEase of establishing planning modelVSAvoidApplicability to continuous state spaces
Core Design Contradiction:
Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent replaces the traditional mechanical/discrete state space modeling approach with a neural network-based continuous state space representation. The neural network learns to map continuous physical states to discrete planning states, substituting the need for manual discrete model construction with a learned continuous representation that can handle high-dimensional physical systems.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the state space representation from discrete to continuous by introducing a neural network that maps continuous physical states to latent planning states. This parameter change allows the system to handle continuous and high-dimensional states while maintaining the structured approach needed for planning.

Inventive Principle:
Principle #35Parameter changes

2Extent of automation

If CNN-based architectures are applied on 2D lattices as state spaces, then value iteration networks can be trained end-to-end, but this imposes restrictions on the models that can be learnt and requires prior knowledge of state space

Engineering Contradiction:
ImproveEnd-to-end training capabilityVSAvoidRestriction on learnable models
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent moves from 2D lattice-based state spaces to a continuous state space represented in a different dimensional framework. By using a neural network to map continuous states to a latent space, the system eliminates the restriction of 2D lattice structures while maintaining the ability to perform end-to-end training through backpropagation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces a dynamic, learnable state space representation that adapts to the specific problem domain. Instead of fixing the state space structure a-priori as in CNN-based 2D lattice approaches, the neural network learns the appropriate representation dynamically during training, increasing the range of learnable models.

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If state space is not known a-priori, then the approach can be more flexible, but standard Markov decision process solving methods cannot be directly applied

Engineering Contradiction:
ImproveFlexibility without prior state space knowledgeVSAvoidAbility to solve planning problem
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The patent performs preliminary action by training the neural network to learn the state space representation and transition dynamics before actual planning occurs. The pre-training phase learns encoder functions and transition models from data, preparing the system for subsequent planning tasks without requiring a-priori knowledge of the specific state space structure.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary neural network that bridges the gap between unknown continuous state spaces and structured planning problems. The neural network acts as a mediator that learns to represent continuous states in a form suitable for planning, enabling standard planning methods to be applied after the intermediary learning stage.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3770820B1Machine learning planner for a physical system
Publication Date: 2024.10.30 ROBERT BOSCH GMBH
  • EP3770820B1 patent drawingFigure 1a~1b
  • EP3770820B1 patent drawingFigure 1c~1d
  • EP3770820B1 patent drawingFigure 2a~2b

AI summary

Some embodiments are directed to a machine learning device for learning a planner for a physical system. A machine-learnable encoder function may be configured to map an observable state to a latent state in a latent space, and a machine-learnable latent transition function may be configured to map an action and a first latent state to a second latent state.