RESUMO
Introduction: In Interactive Task Learning (ITL), an agent learns a new task through natural interaction with a human instructor. Behavior Trees (BTs) offer a reactive, modular, and interpretable way of encoding task descriptions but have not yet been applied a lot in robotic ITL settings. Most existing approaches that learn a BT from human demonstrations require the user to specify each action step-by-step or do not allow for adapting a learned BT without the need to repeat the entire teaching process from scratch. Method: We propose a new framework to directly learn a BT from only a few human task demonstrations recorded as RGB-D video streams. We automatically extract continuous pre- and post-conditions for BT action nodes from visual features and use a Backchaining approach to build a reactive BT. In a user study on how non-experts provide and vary demonstrations, we identify three common failure cases of an BT learned from potentially imperfect initial human demonstrations. We offer a way to interactively resolve these failure cases by refining the existing BT through interaction with a user over a web-interface. Specifically, failure cases or unknown states are detected automatically during the execution of a learned BT and the initial BT is adjusted or extended according to the provided user input. Evaluation and results: We evaluate our approach on a robotic trash disposal task with 20 human participants and demonstrate that our method is capable of learning reactive BTs from only a few human demonstrations and interactively resolving possible failure cases at runtime.
RESUMO
OBJECTIVE: Hot iron disbudding of calves is a stressful and painful procedure. Previous parts of an ongoing comprehensive study on disbudding in dairy calves dealt with various types of pain management and the direct effects of the procedure on physiological, biochemical and behavioral processes. The goal of this study part was to investigate the effects of the disbudding procedure per se, pain management and the age of the calf at the time of disbudding on the health status of the calf. MATERIALS AND METHODS: A total of 337 German Holstein heifer calves were used for this prospective, randomized and triple-blinded study. The calves were disbudded at 4-10 days or at 15-28 days of age. Each calf was randomly assigned to one of 9 treatment groups, which differed with respect to pain management (sedation, local anesthesia, nonsteroidal antiinflammatory drugs, placebo). All but the sham-disbudded calves underwent hot iron disbudding and all calves were monitored clinically before and until 4 weeks after the procedure. The findings were analyzed using valuation scores and a threshold model of the SAS software. RESULTS: Disbudding exhibited adverse effects on respiratory health. Calves undergoing sham disbudding experienced the lowest incidence of respiratory disease and calves that did not receive any anesthesia or pain medication displayed the highest frequency. All treatments showed mitigating effects on the incidence of respiratory tract diseases, however the effects varied with the type of pain management. Fever was less common in calves that were disbudded early in life than calves that underwent disbudding at an older age. CONCLUSION: Disbudding of young calves poses a risk to respiratory health. If breeding of polled offspring is not possible or when farming of horned cattle is not feasible, the risk of respiratory disease induced by disbudding can be minimized by adequate pain management. Disbudding of very young calves is feasible and recommended. CLINICAL RELEVANCE: The present study underlines the importance of optimal pain management during disbudding of dairy calves.
