Trailer Path Planning Using Off-Lattice Motion Primitives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
On-lattice path planning algorithms for trailer-based vehicles face limitations such as restricted path feasibility, compromised path quality, and high computational complexity due to the need for pre-computed motion primitives and heuristic look-up tables, which are not suitable for real-time and online motion planning.
Innovation Solution
The development of off-lattice path planning techniques that allow for real-time and accurate path generation by parameterizing motion primitives over a reduced pseudo-trailer-configuration, enabling the exploration of nodes beyond pre-defined state lattices and using machine learning to estimate the cost-to-go function, thereby reducing computational complexity and memory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If on-lattice path planning algorithms use pre-defined state lattices and pre-computed motion primitives, then path planning feasibility is improved, but path quality is compromised and computational complexity increases
Solution Approach 1:
The patent segments the path planning process into two distinct phases: offline phase where a simplified state lattice is used to generate a preliminary path, and online phase where continuous state space optimization refines the path. This segmentation allows the system to benefit from both the computational efficiency of discrete lattice methods and the path quality of continuous optimization, resolving the contradiction between feasibility and quality.
Solution Approach 2:
The patent applies preliminary action by pre-computing a coarse path using on-lattice algorithms with pre-defined state lattices and motion primitives. This preliminary path serves as an initial solution that guarantees feasibility, which is then refined in the online phase. The preliminary action ensures reliability while enabling subsequent optimization for improved path quality.
2Device complexity
If on-lattice path planning algorithms use pre-defined state lattices, then computational complexity is reduced, but path planning feasibility is compromised
Solution Approach 1:
The patent segments the computational process into offline pre-computation (using simplified lattices for efficiency) and online refinement (using continuous state space for completeness). This segmentation allows the system to achieve low computational complexity during real-time operation while maintaining path planning feasibility through the offline preparation phase.
Solution Approach 2:
The patent performs preliminary action by pre-computing motion primitives and heuristic functions offline using simplified state lattices. This preliminary computation stores results that can be quickly retrieved and applied online, reducing real-time computational complexity while ensuring path planning feasibility is maintained through the pre-computed structures.
3Manufacturing precision
If a large set of motion primitives are used to ensure transition between lattice nodes, then path planning accuracy is improved, but computational complexity and memory requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing a library of motion primitives offline that cover transitions between lattice nodes. These pre-computed primitives are stored in memory for quick retrieval during online planning, eliminating the need to compute them in real-time. This approach improves path planning accuracy while keeping online computational complexity low.
Solution Approach 2:
The patent makes the set of motion primitives dynamic by selecting and applying only those primitives that are relevant to the current state and goal, rather than exhaustively evaluating all possible primitives. This dynamic selection process improves accuracy for relevant transitions while reducing computational complexity by avoiding evaluation of irrelevant primitives.
4Productivity
If heuristic look-up tables are used for cost estimation, then path planning speed is improved, but memory burden increases
Solution Approach 1:
The patent applies preliminary action by pre-computing heuristic cost values for lattice nodes offline and storing them in look-up tables. During online path planning, these pre-computed heuristic values are retrieved in constant time without requiring complex calculations, thus improving path planning speed. The memory burden is accepted as a trade-off for the speed improvement, but the offline computation eliminates real-time computational overhead.
Data Source
AI summary
A system for controlling a motion of a trailer-based vehicle from an initial state till a target state, wherein each state includes a location and a heading of the trailer-based vehicle. The trailer-based vehicle includes a tractor and at least one trailer attached to the tractor such that the motion of the tractor controls the motion of the trailer. The system is configured to collect a set of motion primitives parameterized on quantized pseudo-trailer-configuration from a finite set of quantized pseudo-trailer-configurations, and repetitively select a node based on corresponding cost, and apply motion primitives at the selected node based on corresponding pseudo-trailer-configuration to add new nodes having pseudo-trailer-configurations belonging to set of all possible values. The system is configured to connect a sequence of multiple motion primitives into motion path connecting initial state with target state and control the motion of the tractor-trailer according to the motion path.