One of the core challenges of long-term autonomy is the environmental dynamics that agents must interact with. Some of these dynamics are driven by reliable cyclic processes, and thus are predictable. The most dominant of these is the daily solar cycle, which drives both natural phenomena like weather, as well as the activity of animals and humans. Circadian clocks are a widespread solution in nature to help organisms adapt to these dynamics, and demonstrate that many organisms benefit from maintaining simple models of their environments and how they change. Drawing inspiration from circadian systems, this work models relevant environmental states as times series, allowing for forecasts of the state to be generated without any knowledge of the underlying physics. These forecasts are treated as special percepts in a behavior-based architecture; providing estimates of the future state rather than measurements of the current state. They are incorporated into an ethologically based action-selection mechanism, where they influence the activation levels of behaviors. The approach was validated on a simulated agricultural task: a solar-powered agent monitoring pest populations. By using the artificial circadian system to leverage the forecasted state, the agent was able to improve performance and energy management.
AmbrusR.EkekrantzJ.FolkessonJ.JensfeltP. (2015). Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference (pp. 5678–5685). IEEE. Retrieved from https://ieeexplore.ieee.org/document/7354183
2.
ArkinR. C. (1998). Behavior-based robotics. Cambridge: The MIT press.
3.
ArkinR. C.EgerstedtM. (2015, December). Temporal heterogeneity and the value of slowness in robotic systems. In Robotics and Biomimetics (ROBIO), 2015 IEEE International Conference (pp. 1000–1005). IEEE. Retrieved from https://ieeexplore.ieee.org/document/7418902
4.
ArkinR. C.FujitaM.TakagiT.HasegawaR. (2003). An ethological and emotional basis for human–robot interaction. Robotics and Autonomous Systems, 42, 191–201.
5.
AschoffJ. (1967). Adaptive cycles: Their significance for defining environmental hazards. International Journal of Biometeorology, 11, 255–278.
6.
BacherP.MadsenH.NielsenH. A. (2009). Online short-term solar power forecasting. Solar Energy, 83, 1772–1783.
7.
BlumbergB. (1994, July). Action-selection in Hamsterdam: Lessons from ethology. In Third International Conference on the Simulation of Adaptive Behavior (pp. 108–117). Retrieved from https://dl.acm.org/citation.cfm?id=189843
8.
BoyanJ. A.LittmanM. L. (2001). Exact solutions to time-dependent MDPs. Advances in Neural Information Processing Systems, 13, 1026–1032.
9.
BuchliB.SuttonF.BeutelJ.ThieleL. (2014, November). Dynamic power management for long-term energy neutral operation of solar energy harvesting systems. In Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems (pp. 31–45). ACM. Retrieved from https://dl.acm.org/citation.cfm?id=2668333
10.
ChernovaS.ArkinR. C. (2007). From deliberative to routine behaviors: A cognitively inspired action-selection mechanism for routine behavior capture. Adaptive Behavior, 15, 199–216.
11.
ClevelandR. B.ClevelandW. S.McRaeJ. E.TerpenningI. (1990). STL: A seasonal-trend decomposition. Journal of Official Statistics, 6, 3–73.
12.
DeCourseyP. J.KrulasJ. R.MeleG.HolleyD. C. (1997). Circadian performance of suprachiasmatic nuclei (SCN)-lesioned antelope ground squirrels in a desert enclosure. Physiology & Behavior, 62, 1099–1108.
13.
FleuryF.AllemandR.VavreF.FouilletP.BouletreauM. (2000). Adaptive significance of a circadian clock: Temporal segregation of activities reduces intrinsic competitive inferiority in Drosophila parasitoids. Proceedings of the Royal Society of London Series B: Biological Sciences, 267, 1005–1010.
HyndmanR.KoehlerA. B.OrdJ. K.SnyderR. D. (2008). Forecasting with exponential smoothing: The state space approach. Berlin, Germany: Springer Science & Business Media.
16.
KansalA.HsuJ.ZahediS.SrivastavaM. B. (2007). Power management in energy harvesting sensor networks. ACM Transactions on Embedded Computing Systems (TECS), 6(4), Article 32.
17.
KindlmannP.ArditiR.DixonA. F. G. (2004). A simple aphid population model. In SimonJ.-C.DedryverC.-A.RispeC.HulléM. (Eds.), Aphids in a new millennium (pp. 325–330). Paris, France: INRA.
18.
KrajníkT.FentanesJ. P.SantosJ. M.DuckettT. (2017). FreMEn: Frequency map enhancement for long-term mobile robot autonomy in changing environments. IEEE Transactions on Robotics, 33, 964–977.
19.
LiuL.SukhatmeG. S. (2018). A solution to time-varying Markov decision processes. IEEE Robotics and Automation Letters, 3, 1631–1638.
20.
LorenzE.HurkaJ.HeinemannD.BeyerH. G. (2009). Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2, 2–10.
21.
MitsouN. C.TzafestasC. S. (2007, June). Temporal occupancy grid for mobile robot dynamic environment mapping. In 2007 Mediterranean Conference on Control & Automation (pp. 1–8). IEEE. Retrieved from https://ieeexplore.ieee.org/document/4433892
OatleyK. (1974). Circadian rhythms and representations of the environment in motivational systems. In McFarlandD. J. (Ed.), Motivational control systems analysis (pp. 427–459). Oxford, UK: Academic Press.
24.
O’BrienM. J.ArkinR. C. (2017). Modeling temporally dynamic environments for persistent autonomous agents. In RusV.MarkovZ. (Eds.), Proceedings of the Thirtieth International Florida Artificial Intelligence Research Society Conference (pp. 442–448). Palo Alto, CA: AAAI Press.
25.
ParanjpeD. A.SharmaV. (2005). Evolution of temporal order in living organisms. Journal of Circadian Rhythms, 3(1), Article 7.
26.
RichardsJ.GumzM. L. (2013). Mechanism of the circadian clock in physiology. American Journal of Physiology-Regulatory, Integrative and Comparative Physiology, 304(12), R1053–R1064.
27.
RichterM.SandamirskayaY.SchönerG. (2012, October). A robotic architecture for action selection and behavioral organization inspired by human cognition. In Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference (pp. 2457–2464). IEEE. Retrieved from https://ieeexplore.ieee.org/document/6386153
28.
RoennebergT.DaanS.MerrowM. (2003). The art of entrainment. Journal of Biological Rhythms, 18, 183–194.
VelayudhanL.ArkinR. C. (2017, December). Sloth and slow loris inspired behavioral controller for a robotic agent. In. Robotics and Biomimetics (ROBIO), 2017 IEEE International Conference (pp. 1880–1885). IEEE. Retrieved from https://ieeexplore.ieee.org/document/8324693
