Skip to content

Latest commit

 

History

History
40 lines (29 loc) · 5.84 KB

IEEE-Transactions-on-Robotics_TRO.md

File metadata and controls

40 lines (29 loc) · 5.84 KB
Raw

TRO (IEEE Transactions on Robotics)

  • Song, S., Kim, D. and Choi, S., 2022. View path planning via online multiview stereo for 3-d modeling of large-scale structures. IEEE Transactions on Robotics, 38(1), pp.372-390. [ www ] ( CMA-ES | Continuous Optimization )
    • "An optimal polynomial trajectory is obtained by the covariance matrix adaptation evolution strategy (CMA-ES). The CMA-ES is based on evolutionary algorithms, which work equally well for both nonlinear and nonconvex problems in continuous space."
      • M. Popovi´c et al., “An informative path planning framework for UAVbased terrain monitoring,” Auton. Robots, vol. 44, 6, pp. 889–911, 2020.
      • N. Hansen, “The CMA evolution strategy: A comparing review,” in Towards A New Evolutionary Computation. Berlin, Germany: Springer, 2006, pp. 75–102.
  • Chen, T., Wang, L., Haas-Heger, M. and Ciocarlie, M., 2020. Underactuation design for tendon-driven hands via optimization of mechanically realizable manifolds in posture and torque spaces. IEEE Transactions on Robotics, 36(3), pp.708-723. [ www ] ( CMA-ES | Continuous Optimization )
    • "Although the inner layer is convex, the outer layer is not, and is not trivial to be reformulated as a convex problem. Therefore, we decided to use a stochastic global search. The optimizer we chose is the covariance matrix adaptation evolutionary strategy (CMA-ES). It is a stochastic, derivative-free algorithm for black-box global optimization, in which the covariance matrix of the distribution of the candidate solutions is updated adaptively in each generation. This method learns a stochastic second-order approximation of the objective, and drives the candidate solutions to the optimum, even when the function is ill-conditioned."
      • N. Hansen and A. Ostermeier, “Completely derandomized self-adaptation in evolution strategies,” Evol. Comput., vol. 9, no. 2, pp. 159–195, 2001.
      • N. Hansen, S. D. Müller, and P. Koumoutsakos, “Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES),” Evol. Comput., vol. 11, no. 1, pp. 1–18, 2003.
  • Mastalli, C., Havoutis, I., Focchi, M., Caldwell, D.G. and Semini, C., 2020. Motion planning for quadrupedal locomotion: Coupled planning, terrain mapping, and whole-body control. IEEE Transactions on Robotics, 36(6), pp.1635-1648.
    • "We solve this trajectory optimization problem using the covariance matrix adaptation evolution strategy (CMA-ES). Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is capable of handling optimization problems that have multiple local minima and discontinuous gradients. An important feature since the terrain cost-map introduces multiple local minima and gradient discontinuity."
      • N. Hansen, “CMA-ES: A function value free second order optimization method,” in Proc. PGMO COPI, 2014, pp. 479–501.
  • Kim, M. and Collins, S.H., 2017. Once-per-step control of ankle push-off work improves balance in a three-dimensional simulation of bipedal walking. IEEE Transactions on Robotics, 33(2), pp.406-418. [ www ] ( CMA-ES | Continuous Optimization )
    • "We develop new controllers that have been optimized for disturbance tolerance using an evolutionary strategy for each combination of control input, speed and disturbance."
      • N. Hansen, “The CMA evolution strategy: A comparing review,” in Towards a New Evolutionary Computation, J. A. Lozano, Ed. Berlin: Springer, 2006, pp. 75–102.
  • Taylor, Z. and Nieto, J., 2016. Motion-based calibration of multimodal sensor extrinsics and timing offset estimation. IEEE Transactions on Robotics, 32(5), pp.1215-1229. [ www ] ( CMA-ES | Nelder–Mead | Continuous Optimization )
    • "To meet these requirements, we make use of the CMA-ES optimization technique."
    • "From this starting point, a CMA-ES optimizer is first run considering the entire search space. This was done by setting the initial multivariate Gaussian to have a σ that is 50% of the extent of our search space. Once this optimization has been performed, the approach is rerun, this time making use of the variance estimate provided by the motion stage and using this information to initialize CMA-ES’s Gaussian distribution."
      • N. Hansen and A. Ostermeier, “Adapting arbitrary normal mutation distributions in evolution strategies: The covariance matrix adaptation,” in Proc. IEEE Int. Conf. Evol. Comput., 1996, pp. 312–317.

2021

Favaro, A., Segato, A., Muretti, F. and De Momi, E., 2021. An evolutionary-optimized surgical path planner for a programmable bevel-tip needle. IEEE Transactions on Robotics, 37(4), pp.1039-1050. [ www ]

2012

Hiller, J. and Lipson, H., 2012. Automatic design and manufacture of soft robots. IEEE Transactions on Robotics, 28(2), pp.457-466. [ www ] (ER | GA)

2007

Zykov, V., Mytilinaios, E., Desnoyer, M. and Lipson, H., 2007. Evolved and designed self-reproducing modular robotics. IEEE Transactions on Robotics, 23(2), pp.308-319. [ www ]

2006

Paul, C., Valero-Cuevas, F.J. and Lipson, H., 2006. Design and control of tensegrity robots for locomotion. IEEE Transactions on Robotics, 22(5), pp.944-957. [ www ] (ER | GA)

2003

Hornby, G.S., Lipson, H. and Pollack, J.B., 2003. Generative representations for the automated design of modular physical robots. IEEE Transactions on Robotics and Automation, 19(4), pp.703-719. [ www ]