Odest Chadwicke Jenkins

NASA NTRSDate not supplied

Comparing Human Input in RViz and Virtual Reality Interfaces for 3D Object Manipulation Tasks

Effective human-in-the-loop robot control requires intuitive and easy to use interfaces. We present a within-subjects user study design to compare the ease of use of interfaces for human-robot teleoperation, specifically the ROS 3D visualization tool RViz and a virtual reality interface. Our proposed study will determine which interface is easiest to use and minimizes operator cognitive load in shared autonomy tasks.

Emily Sheetz↗

NASA NTRSDate not supplied

Composable Semantic Frames for Grounding Language in Robot Control Primitives

As robots become increasingly capable of taking on challenging tasks, we want robots to be commanded in intuitive ways. Non-expert users in particular should be able to communicate with robots about task goals. As a result, modes of interaction such as language have gained interest for commanding robots. We present composable semantic frames, which ground commands in robot control primitives by composing high-level commands from lower-level commands. We demonstrate that composable semantic frames allow robots to understand and execute a variety of challenging commands, such as those involving multiple verb meanings, command variations, and compound nouns. The robot quickly processes composable semantic frames and accurately grounds and executes the commanded tasks, demonstrating the power of composable semantic frames for allowing users to intuitively interact with robots.

Emily Sheetz↗