dc.contributor.authorPham, Minh Khang
dc.date.accessioned2019-01-07T00:32:41Z
dc.date.available2019-01-07T00:32:41Z
dc.date.issued2018
dc.identifier.urihttp://hdl.handle.net/10356/76393
dc.description.abstractThe paper propose a new way of solving the Pallet Packing Problem by modelling it as a Markov decision process. This allows the program to make decisions step-by-step based only on the current state and adapt to any error in execution. By applying reinforcement learning techniques, an agent can be trained from simulation to learn a model-free near-optimal policy that maximize the discounted cumulative rewards, which is proportional to the original objective function. Experiments show positive results on simulations involving packing up to 12 boxes into a grid-based pallet of size 8*8*6.en_US
dc.format.extent38 p.en_US
dc.language.isoenen_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Roboticsen_US
dc.subjectDRNTU::Engineering::Mechanical engineering::Robotsen_US
dc.titleManipulation task planning for heterogeneous object stacking based on reinforcement learningen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorDomenico Campoloen_US
dc.contributor.schoolSchool of Mechanical and Aerospace Engineeringen_US
dc.description.degreeBachelor of Engineering (Mechanical Engineering)en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record