Walmart Apollo, LLC

Amritayan Nayak

Mingang Fu

Deepak R Deshpande

Jing Huang

Minghui Liu

Madhavan Kandhadai Vasantham

Rohit Jain

Pushkar Raj Pande

Li Ji

Anurag Gupta

Prakash Seetharaman

Srinivasan Venkatesan

Syed Aman

Deyi Zhang

Akshara Dendi

Kumar Malyala

This application relates to apparatus and methods for generating and implementing a machine learning model in electronic delivery systems to determine delivery routes and times. In some examples, a computing device generates a machine learning model comprising a plurality of indexed binary trees. Each indexed binary tree determines either a first value, or a second value, based on comparing an input to a condition value. The machine learning model can generate prediction values based on the determined values of all indexed binary trees. The machine learning model is trained with historical data. Once trained, the machine learning model's performance is evaluated. Based on the evaluation, the machine learning model may be further refined. Once the machine learning model's performance satisfies requirements, the computing device employs the machine learning model to determine vehicle delivery routes and estimated delivery times.

Apparatus and methods for determining delivery routes and times based on generated machine learning models

Horizontally-scalable systems and methods for scheduling and optimizing deliveries are described herein. At least one scheduler is configured to receive a request to schedule a delivery for an origination location. The request includes a desired time slot. The request is compared to a persistent delivery snapshot for the origination location to determine availability of the desired time slot. An interim delivery snapshot including the requested delivery is generated when the persistent delivery snapshot has an available time slot corresponding to the desired time slot. At least one optimizer is configured to receive the interim delivery snapshot and generate an updated persistent delivery snapshot by applying an optimization process to the interim delivery snapshot.

Systems and methods for combinatorial resource optimization

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform certain acts. The acts can include obtaining a route for delivering one or more orders in a tri-temp trailer from a distribution center to physical stores in a sequence of stops. The route can have an associated assignment of stack groups comprising stacks of pallets. The acts also can include determining a load design for the stacks in the tri-temp trailer based on the sequence of the stops in the route, such that unloading each of the stacks is minimized when the tri-temp trailer delivers the orders to the physical stores. The acts additionally can include outputting the load design to cause the stacks to be loaded in the tri-temp trailer according to the load design for delivery to the physical stores in the sequence of stops. The load design can specify a respective floor spot assignment for each of the stacks. Other embodiments are described.

Automatic generation of load design

A system for generating a geographically-clustered routing solution includes a computer system configured to receive a plurality of orders. Each order in the plurality of orders comprises a geographic location. The plurality of orders are clustered into a plurality of clusters based on the geographic location of each order and a routing solution is generated for each of the plurality of clusters. Each routing solution is transmitted to at least one vehicle system.

Clustering regulated VRPTW solver for large scale batch optimization of last mile delivery

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform certain acts. The acts can include obtaining a route for delivering one or more orders in a trailer from a distribution center to physical stores in a sequence of stops. The route can have an associated assignment of stack groups comprising stacks of pallets. The acts also can include determining a load design for the stacks in the trailer based on the sequence of the stops in the route. The acts additionally can include updating the load design using a first simulated annealing to adjust a front-to-rear center-of-gravity of the load design. The acts further can include updating the load design using a second simulated annealing to adjust a side-to-side center-of-gravity of the load design. The acts additionally can include outputting the load design, as updated by the first simulated annealing and the second simulated annealing. The load design can specify a respective floor spot assignment for each of the stacks. Other embodiments are described.

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform certain acts. The acts can include obtaining orders for fulfillment to physical stores from a distribution center. There can be one or more respective stack groups associated with each of the orders. The acts also can include generating a set of feasible route templates for delivering the orders to the physical stores. The acts additionally can include formulating a mixed integer programming formulation for an assignment of the respective stack groups associated with the orders to the set of route templates. The acts further can include using an optimization solver for the mixed integer programming formation to determine the assignment that minimizes an overall cost of delivering the orders to the physical stores from the distribution center. The acts additionally can include outputting the assignment. Other embodiments are described.

Automatic generation of route design

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform receiving orders from physical stores for fulfillment from a distribution center, each of the orders comprising a set of items and a requested delivery date; generating a stack building plan for each of the orders using simulated annealing; obtaining routes for delivering the orders in trailers from the distribution center to the physical stores based at least in part on the stack building plan; and generating a load design for each of the routes to deliver in a trailer of the trailers a load for one or more of the orders, such that floor spot assignments for stacks for each of the one or more of the orders in the load carried by the trailer satisfy sequence-of-delivery constraints and center-of-gravity constraints. Other embodiments are disclosed.

Automatic generation of load and route design

Systems and methods for optimizing delivery vehicle resources (e.g. a plurality of vehicles) are described herein. Available time slots for the plurality of vehicles are determined and presented to a user. In response to receiving a delivery order indicating a selected time slot, the delivery order is assigned to a vehicle from the plurality of vehicles based on a time slot indicated in the delivery order and a set of delivery parameters. A delivery route is calculated for each vehicle having a delivery order based on the set of delivery parameters. An optimized delivery route is calculated for each vehicle having a delivery order based on the set of delivery parameters.

A load and route assignment system is provided and generally includes a computing device and a database. The database may store historical inbound load data and historical outbound load data related to previous inbound and outbound loads. The computing device can obtain and aggregate the historical inbound and outbound load data from the database, and determine an optimal path based on the aggregated historical data. The optimal path, along with load attribute data, may be stored in the database as a tour template for future load executions. The computing device may use the tour templates to determine future load assignments to vehicles. The computing device may also obtain real-time load requests, and match them to one or more of a plurality of tour templates. The computing device may assign the matched real-time load requests to a vehicle for execution in accordance with the corresponding load and tour template.

Growing community of inventors

Santa Clara, CA, United States of America

Amritayan Nayak