No abstract

As in-space exploration increases, autonomous systems will play a vital role in building the necessary facilities to support exploration. To this end, an autonomous system must be able to assign tasks in a scheme that efficiently completes all of the jobs in the desired project. This research proposes a flexible job shop problem (FJSP) representation to characterize an autonomous assembly project and then proposes both a mixed integer programming (MIP) solution formulation and a reinforcement learning (RL) solution formulation. The MIP formulation encodes all of the constraints and interjob dynamics a priori and was able to solve for the optimal solution to minimize the makespan. The RL formulation did not converge to an optimal solution but did successfully learn implicitly interjob dynamics through interaction with the reward function. Future work will include developing a solution formulation that utilizes the strengths of both proposed solution methods to handle scaling in size and complexity.

The purpose of this study was to develop archival tagging methods for goosefish Lophius americanus (more commonly known as monkfish), a species thought to be highly susceptible to capture and tagging mortality and very difficult to maintain in captivity. Archival tags were implanted subcutaneously near the second dorsal fin using sanitary surgical methods. A streamer attached to the tag extended through the skin and provided an externally visible tag. Mortality of both tagged and control fish was high (39–44%) in laboratory experiments but did not differ significantly; thus, tagging did not increase mortality. Tag retention was 100% through 6 weeks, but 38% of the incisions on tagged fish showed possible signs of opening. Two of four tagged fish held for up to 6 months expelled their tags. We hypothesize that the streamer prevented complete healing of the incision and led to tag loss. We conclude that archival tagging of monkfish could be successful but recommend that archival tags be completely enclosed if implanted subcutaneously.

Hyperspectral images have been used in agricultural and geoscience studies since the 1980s, mostly from a satellite or aerial platform.(Rinker 1990) The benefit of hyperspectral images is also their main drawback in that they are very high dimensional data, usually on the order of 100 times greater spectral resolution than a traditional RGB camera. A forthcoming study has attempted to leverage hyperspectral imaging to improve classification accuracy in ground level sensor applications.

No abstract