Search

We propose a novel iterative approach for crossing the reality gap that utilises live robot rollouts and differentiable physics. Our method, RealityGrad, demonstrates for the first time, an efficient sim2real transfer in combination with a real2sim model optimisation for closing the reality gap. Differentiable physics has become an alluring alternative to classical rigid-body simulation due to the current culmination of automatic differentiation libraries, compute and non-linear optimisation libraries. Our method builds on this progress and employs differentiable physics for efficient trajectory optimisation. We demonstrate RealitGrad on a dynamic control task for a serial link robot manipulator and present results that show its efficiency and ability to quickly improve not just the robot's performance in real world tasks but also enhance the simulation model for future tasks. One iteration of RealityGrad takes less than 22 minutes on a desktop computer while reducing the error by 2/3, making it efficient compared to other sim2real methods in both compute and time. Our methodology and application of differentiable physics establishes a promising approach for crossing the reality gap and has great potential for scaling to complex environments., Comment: 8 Pages

The large demand for simulated data has made the reality gap a problem on the forefront of robotics. We propose a method to traverse the gap by tuning available simulation parameters. Through the optimisation of physics engine parameters, we show that we are able to narrow the gap between simulated solutions and a real world dataset, and thus allow more ready transfer of leaned behaviours between the two. We subsequently gain understanding as to the importance of specific simulator parameters, which is of broad interest to the robotic machine learning community. We find that even optimised for different tasks that different physics engine perform better in certain scenarios and that friction and maximum actuator velocity are tightly bounded parameters that greatly impact the transference of simulated solutions., Comment: 8 Pages, Submitted to IROS2020

We present a benchmark to facilitate simulated manipulation; an attempt to overcome the obstacles of physical benchmarks through the distribution of a real world, ground truth dataset. Users are given various simulated manipulation tasks with assigned protocols having the objective of replicating the real world results of a recorded dataset. The benchmark comprises of a range of metrics used to characterise the successes of submitted environments whilst providing insight into their deficiencies. We apply our benchmark to two simulation environments, PyBullet and V-Rep, and publish the results. All materials required to benchmark an environment, including protocols and the dataset, can be found at the benchmarks' website https://research.csiro.au/robotics/manipulation-benchmark/., Comment: Accepted to the IEEE Robotics and Automation Letters (RA-L) Special Issue: Benchmarking Protocols for Robotic Manipulation (2019)

Numerous organisations collect data in the Great Barrier Reef (GBR), but they are rarely analysed together due to different program objectives, methods, and data quality. We developed a weighted spatiotemporal Bayesian model and used it to integrate image based hard coral data collected by professional and citizen scientists, who captured and or classified underwater images. We used the model to predict coral cover across the GBR with estimates of uncertainty; thus filling gaps in space and time where no data exist. Additional data increased the models predictive ability by 43 percent, but did not affect model inferences about pressures (e.g. bleaching and cyclone damage). Thus, effective integration of professional and high-volume citizen data could enhance the capacity and cost efficiency of monitoring programs. This general approach is equally viable for other variables collected in the marine environment or other ecosystems; opening up new opportunities to integrate data and provide pathways for community engagement and stewardship.

We describe extensions to the siesta density functional theory (dft) code [30], for the simulation of isolated molecules and their absorption spectra. The extensions allow for: - Use of a multi-grid solver for the Poisson equation on a finite dft mesh. Non-periodic, Dirichlet boundary conditions are computed by expansion of the electric multipoles over spherical harmonics. - Truncation of a molecular system by the method of design atom pseudo- potentials of Xiao and Zhang[32]. - Electrostatic potential fitting to determine effective atomic charges. - Derivation of electronic absorption transition energies and oscillator stren- gths from the raw spectra produced by a recently described, order O(N3), time-dependent dft code[21]. The code is furthermore integrated within siesta as a post-processing option.

The search for durable dyes led several past civilizations to develop artificial pigments. Maya Blue (MB), manufactured in pre-Columbian Mesoamerica, is one of the best known examples of an organic-inorganic hybrid material. Its durability is due to the unique association of indigo molecule and palygorskite, a particular fibrous clay occurring in Yucatan. Despite 50 years of sustained interest, the microscopic structure of MB and its relation to the durability remain open questions. Combining new thermogravimetric and synchrotron X-ray diffraction analyses, we show that indigo molecules can diffuse into the channel of the palygorskite during the heating process, replacing zeolitic water and stabilizing the room temperature phases of the clay.

The durability of an organic colour and its resistance against external chemical agents and exposure to light can be significantly enhanced by hybridizing the natural dye with a mineral. In search for stable natural pigments, the present work focuses on the association of indigo blue with several zeolitic matrices (LTA zeolite, mordenite, MFI zeolite). The manufacturing of the hybrid pigment is tested under varying oxidising conditions, using Raman and UV-visible spectrometric techniques. Blending indigo with MFI is shown to yield the most stable composite in all of our artificial indigo pigments. In absence of defects and substituted cations such as aluminum in the framework of the MFI zeolite matrix, we show that matching the pore size with the dimensions of the guest indigo molecule is the key factor. The evidence for the high colour stability of indigo@MFI opens a new path for modeling the stability of indigo in various alumino-silicate substrates such as in the historical Maya Blue pigment.

Maya Blue is actually one of the best known examples of an organic-inorganic hybrid material. Yet despite 50 years of sustained interest, its microscopic structure and its relation to durability remain open questions. We address the issue by archaeomimetism: engineering an archaeoinspired pigment, satisfactorily reproducing the colour and chemical stability of Maya Blue. By comparing and contrasting ancient pigment and the new analogue, we deduce a new explanation for this durability.