In this work, we present an inverse reinforcement learning approach for solving the problem of task sequencing for robots in complex manufacturing processes. Our proposed framework is adaptable to variations in process and can perform sequencing for entirely new parts. We prescribe an approach to capture feature interactions in a demonstration dataset based on a metric that computes feature interaction coverage. We then actively learn the expert's policy by keeping the expert in the loop. Our training and testing results reveal that our model can successfully learn the expert's policy. We demonstrate the performance of our method on a real-world manufacturing application where we transfer the policy for task sequencing to a manipulator. Our experiments show that the robot can perform these tasks to produce human-competitive performance. Code and video can be found at: https://sites.google.com/usc.edu/irlfortasksequencing

Virtual human expressions can shape user behavior [1, 2, 3], yet in negotiation, findings have been underwhelming. For example, human negotiators can use anger to claim value (i.e., extract concessions) [4], but anger has no effect when exhibited by a virtual human [5]. Other psychological work suggests that emotions can create value (e.g., happy negotiators can better discover tradeoffs across issues that "grow the pie"), but little research has examined how virtual human expressions shape value creation. Here we present an agent architecture and pilot study that examines differences between how the emotional expressions of human and virtual-human opponents shape value claiming and value creation. We replicate the finding that virtual human anger fails to influence value claiming but discover counter-intuitive findings on value creation. We argue these findings highlight the potential for intelligent virtual humans to yield insight into human psychology.

Composites are increasingly becoming a material of choice in the aerospace and automotive industries. Currently, many composite parts are produced by manually laying up sheets on complex molds. Composite sheet layup requires executing two main tasks: (1) grasping a sheet and (2) draping it on the mold. Automating the layup process requires automation of these two tasks. This paper is focused on the automation of the grasping task using robots. This requires an automated generation of grasp plans to enable robots to hold the sheet during the draping process. We present a simulation-based approach for determining robot grasp locations on the composite sheets. We also present an intervention controller that uses a real-time sheet tracking system during plan execution and can prevent failures. We demonstrate the performance of the developed system using a large complex part.