Exploring Non-Expert Robot Programming Through Crowdsourcing

Abstract

A longstanding barrier to deploying robots in the real world is the ongoing need to author robot behavior. Remote data collection–particularly crowdsourcing—is increasingly receiving interest. In this paper, we make the argument to scale robot programming to the crowd and present an initial investigation of the feasibility of this proposed method. Using an off-the-shelf visual programming interface, non-experts created simple robot programs for two typical robot tasks (navigation and pick-and-place). Each needed four subtasks with an increasing number of programming statements (if statement, while loop, variables) for successful completion of the programs. Initial findings of an online study (N = 279) indicate that non-experts, after minimal instruction, were able to create simple programs using an off-the-shelf visual programming interface. We discuss our findings and identify future avenues for this line of research.

SpaTiaL: Monitoring and Planning of Robotic Tasks Using Spatio-Temporal Logic Specifications

“…Moreover, we will investigate optimization-based controllers to satisfy spatial relations in our planning approach, see Lemma 2. Lastly, we like to develop approaches to learn specifications from demonstrations and to leverage users to correct specifications (Kress-Gazit et al, 2008van Waveren et al, 2021;Kent et al, 2017;Zhang et al, 2021;van Waveren et al, 2022).…”

SpaTiaL: monitoring and planning of robotic tasks using spatio-temporal logic specifications

“…To address the computation times, we will investigate optimization-based approaches to satisfy spatial relations in our planning approach. Lastly, we like to develop approaches to learn specifications from demonstrations and to leverage users to correct specifications (Kress-Gazit et al, 2008, 2021van Waveren et al, 2021;Kent et al, 2017;Zhang et al, 2021;van Waveren et al, 2022).…”

Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies

“…We use natural language as an intuitive way for inexperienced users to instruct the robot [32], it allows us to analyze whether people understand the task, it reduces the risk of having the interface design as a confounding factor on task performance, and it can be translated into code [33]. There is a large body of work that focuses on NE robot programming, e.g., [34]- [38]. While that is not our focus, we did ask people to code their solution using the Google Blockly interface [39], to get an idea how this compares to natural language.…”