In collaboration with the Early Childhood Cognition Center at MIT BCS, we are developing sensor-enabled toys and infant affect sensors with the goal to understand how children on the autism spectrum use patterns of evidence to learn causal relationships and the extent with which this is state-dependent. We investigate in what respects, if any, causal learning is different in comparison to typically developing children. The results of this research will inform the design of new object-based technologies for language and communication learning.