Collaborating Authors

NeRP: Neural Rearrangement Planning for Unknown Objects Artificial Intelligence

Robots will be expected to manipulate a wide variety of objects in complex and arbitrary ways as they become more widely used in human environments. As such, the rearrangement of objects has been noted to be an important benchmark for AI capabilities in recent years. We propose NeRP (Neural Rearrangement Planning), a deep learning based approach for multi-step neural object rearrangement planning which works with never-before-seen objects, that is trained on simulation data, and generalizes to the real world. We compare NeRP to several naive and model-based baselines, demonstrating that our approach is measurably better and can efficiently arrange unseen objects in fewer steps and with less planning time. Finally, we demonstrate it on several challenging rearrangement problems in the real world.

[Report] Submillisecond organic synthesis: Outpacing Fries rearrangement through microfluidic rapid mixing


Chemistry relies on encounters between reactive partners. Sometimes one of the partners changes shape during the wait, spoiling the desired outcome. Kim et al. designed a microfluidic device to keep such botched encounters from happening. The device operates at low temperatures to keep individual reactants from isomerizing. It also achieves fast flow rates to maximize encounters between reactants on a microsecond time scale.

Fulham boss Parker angry at 'scandalous' Spurs rearrangement

BBC News

Fulham manager Scott Parker says it is "scandalous" Wednesday's match against Tottenham was only confirmed on Monday.

Genome Rearrangement and Planning: Revisited

AAAI Conferences

Evolutionary trees of species can be reconstructed by pairwise comparison of their entire genomes. Such a comparison can be quantified by determining the number of events that change the order of genes in a genome. Earlier Erdem and Tillier formulated the pairwise comparison of entire genomes as the problem of planning rearrangement events that transform one genome to the other. We reformulate this problem as a planning problem to extend its applicability to genomes with multiple copies of genes and with unequal gene content, and illustrate its applicability and effectiveness on three real datasets: mitochondrial genomes of Metazoa, chloroplast genomes of Campanulaceae, chloroplast genomes of various land plants and green algae.

Structural basis of cooling agent and lipid sensing by the cold-activated TRPM8 channel


These structures reveal that the binding pocket for cooling agents is located at the cavity formed by the voltage-sensor like domain (VSLD) and the TRP domain (see panel B in the figure). They illustrate the structural bases for the recognition of menthol and icilin by TRPM8 and explain why Ca2 is required for icilin binding in TRPM8. These structures and subsequent functional studies unveil the unanticipated location for PIP2 binding at the membrane interfacial cavity established by multiple key subdomains in TRPM8 (see panel B in the figure). Notably, PIP2 can bind to the interfacial cavity in two different modes: partially or fully engaged. Furthermore, structural analyses reveal the molecular basis for the allosteric coupling between PIP2 and cooling agonists in TRPM8.