Search

Large language models encode a vast amount of semantic knowledge and possess remarkable understanding and reasoning capabilities. Previous research has explored how to ground language models in robotic tasks to ensure that the sequences generated by the language model are both logically correct and practically executable. However, low-level execution may deviate from the high-level plan due to environmental perturbations or imperfect controller design. In this paper, we propose DoReMi, a novel language model grounding framework that enables immediate Detection and Recovery from Misalignments between plan and execution. Specifically, during low-level skill execution, we use a vision question answering (VQA) model to regularly detect plan-execution misalignments. If certain misalignment occurs, our method will call the language model to re-plan in order to recover from misalignments. Experiments on various complex tasks including robot arms and humanoid robots demonstrate that our method can lead to higher task success rates and shorter task completion times. Videos of DoReMi are available at https://sites.google.com/view/doremi-paper., 22 pages, 12 figures

This paper presents results of investigation of hydraulic conductivity of soil-bentonite backfill (referred as SB backfill) and sodium hexametaphosphate (SHMP)-amended soil-bentonite backfill (referred as SHMP-SB backfill) exposed to lead-impacted groundwater. Lead nitrate (Pb(NO3)2) solutions with various concentrations were tested as permeant liquids for the flexible wall permeameter hydraulic conductivity tests. Series of laboratory experiments were conducted to assess slump height of the backfills, free swell index of conventional bentonite with and without SHMP-amendment, and hydraulic conductivity of the backfills in tap water and Pb(NO3)2 solutions. The results showed that the moisture contents corresponding to the target slump were 38% and 32% for SB and SHMP-SB backfills, respectively. The free swelling index of conventional bentonite in the 50–60 mM Pb(NO3)2 solutions was enhanced with SHMP amendment. The hydraulic conductivity of SB and SHMP-SB backfills increased with increasing concentration of Pb(NO3)2 solutions as expected. The hydraulic conductivity of SHMP-SB backfill was below the commonly accepted value (10−9 m/s) regardless of the type of permeant liquid, whereas hydraulic conductivity of SB backfill was higher than 10−9 m/s in the Pb(NO3)2 solutions with concentrations of 50 and 500 mM.

This study aims to investigate the membrane and diffusion behavior of a novel vertical cutoff wall backfill comprised of reactive magnesium-activated slag, bentonite and sand (referred as MSBS backfill) for the containment of heavy metals in groundwater. The MSBS backfill specimens were subjected to a series of multi-stage chemico-osmotic tests using Pb(NO3)2 and Zn(NO3)2 solutions at different concentrations. Chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor of the backfills were computed. For computing chemico-osmotic efficiency coefficient, the theoretical chemico-osmotic pressure differences were computed using both van't Hoff equation and water activity method. The results showed that the MSBS backfill exhibited semipermeable membrane behavior in tested solutions. The chemico-osmotic efficiency coefficients of the backfills decreased, whereas effective diffusion coefficients of heavy metal cations remained nearly constant, and retardation factors of heavy metal cations increased slightly with the increase of metal concentration. For the range of concentrations of Zn(NO3)2 in this study, the maximum percent error of theoretical chemico-osmotic pressure difference calculated using van't Hoff equation relative to that calculated using water activity method was 14.4%. A comparative assessment of reported chemico-osmotic efficiency coefficient, effective diffusion coefficient, and retardation factor values for various soil-bentonite backfills and geosynthetic clay liners with those for MSBS backfill was performed. Overall, the results are useful to assess containment performance of MSBS vertical cutoff walls at metal-contaminated groundwater sites.