Language-Conditioned Imitation Learning for Robot Manipulation Tasks
This addresses the challenge of improving human-robot communication in manipulation tasks, though it is incremental as it builds on existing imitation learning by adding language conditioning.
The paper tackles the problem of enabling robots to understand natural language commands in imitation learning by introducing a method that incorporates verbal descriptions during training, allowing for fine-grained control and reduced ambiguity, and demonstrates in simulations that it learns language-conditioned manipulation policies for a robot arm with comparisons to alternative methods.
Imitation learning is a popular approach for teaching motor skills to robots. However, most approaches focus on extracting policy parameters from execution traces alone (i.e., motion trajectories and perceptual data). No adequate communication channel exists between the human expert and the robot to describe critical aspects of the task, such as the properties of the target object or the intended shape of the motion. Motivated by insights into the human teaching process, we introduce a method for incorporating unstructured natural language into imitation learning. At training time, the expert can provide demonstrations along with verbal descriptions in order to describe the underlying intent (e.g., "go to the large green bowl"). The training process then interrelates these two modalities to encode the correlations between language, perception, and motion. The resulting language-conditioned visuomotor policies can be conditioned at runtime on new human commands and instructions, which allows for more fine-grained control over the trained policies while also reducing situational ambiguity. We demonstrate in a set of simulation experiments how our approach can learn language-conditioned manipulation policies for a seven-degree-of-freedom robot arm and compare the results to a variety of alternative methods.