Decoupled EV Routing for Trailer Swaps During Charging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electric tractor-trailers face inefficiencies due to the need for batteries to be fully charged before proceeding, leading to increased travel times and logistical challenges.
Innovation Solution
A computer-implemented method and system using reinforcement learning to optimize the routing of decoupled electric tractors within a network of charging stations, allowing trailers to be swapped and moved without waiting for charging to complete.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If electric tractor-trailers wait for battery charging completion before proceeding, then the battery is fully charged, but travel time increases and logistics efficiency decreases
Solution Approach 1:
The system segments the tractor-trailer into independent components: the electric tractor (rechargeable entity) and the trailer (object). The tractor can be decoupled from the trailer to charge separately at charging stations, while the trailer remains stationary or is transferred to another tractor. This segmentation allows the charging process to occur independently without blocking the overall logistics operation.
Solution Approach 2:
The system performs preliminary routing planning that identifies charging stations along the delivery path and schedules charging stops in advance. The RL agent plans the sequence of actions including when to decouple, where to charge, and when to recouple, optimizing the overall timeline so that charging occurs during periods that minimize impact on delivery schedules.
2Use of energy by moving object
If electric tractors are routed to charging stations, then battery charging is enabled, but routing complexity and decision-making difficulty increase
Solution Approach 1:
The reinforcement learning agent acts as an intermediary that manages the complexity of routing decisions. The RL agent receives inputs about tractor locations, battery states, charging station availability, and delivery requirements, then outputs optimized routing decisions. This intermediary absorbs the computational complexity, presenting simplified decisions to operators while optimizing multiple competing objectives simultaneously.
Solution Approach 2:
The routing system is dynamic and adaptive, with the RL agent continuously learning from new data and adjusting routes in real-time based on changing conditions such as charging station availability, traffic conditions, and battery state of charge. The system adapts its routing strategies dynamically rather than relying on static pre-planned routes.
3Productivity
If trailers are decoupled from electric tractors during charging, then charging delays are reduced, but system coordination complexity increases
Solution Approach 1:
The system segments the tractor-trailer combination into independent entities that can operate separately. The trailer becomes an independent object that can be stationary at a location or transferred to another tractor, while the tractor becomes an independent rechargeable entity that can charge separately. This segmentation enables parallel operations where charging and trailer handling occur independently.
Solution Approach 2:
The system develops universal coordination protocols that can handle multiple scenarios: trailers waiting at locations, trailers being transferred between tractors, multiple tractors charging at different stations, and dynamic reassignment of trailers to tractors. The RL agent learns universal policies that work across diverse situations, reducing the need for scenario-specific complex coordination rules.
Data Source
AI summary
Systems and methods for routing rechargeable entities are described. A processor can receive input indicating a state of a charging network that includes charging stations, rechargeable entities and objects with assigned destinations. The processor can execute, for each object, a decision making process to model decision making by a reinforcement learning agent. The decision making can include applying a sequence of actions on the charging network to change states of the charging network. The processor can determine a sequence of states of the charging network based on results from application of the sequence of actions. The sequence of states can represent transitions of the rechargeable entities and the objects to complete delivery of the objects to the assigned destinations. The processor can generate routing data to direct the rechargeable entities to navigate among the charging stations and to be coupled with the objects according to the sequence of states.