Search for: All records

This paper addresses the problem of preference learning, which aims to align robot behaviors through learning user-specific preferences (e.g. “good pull-over location”) from visual demonstrations. Despite its similarity to learning factualconcepts (e.g. “red door”), preference learning is a fundamentally harder problem due to its subjective nature and the paucity of person-specific training data. We address this problem using a novel framework called SYNAPSE, which is aneuro-symbolic approach designed to efficiently learn preferential concepts from limited data. SYNAPSE represents preferences as neuro-symbolic programs – facilitating inspection of individual parts for alignment – in a domain-specificlanguage (DSL) that operates over images and leverages a novel combination of visual parsing, large language models, and program synthesis to learn programs representing individual preferences. We perform extensive evaluations on various preferential concepts as well as user case studies demonstrating its ability to align well with dissimilar user preferences. Our method significantly outperforms baselines, especially when it comes to out-of-distribution generalization. We show the importance of the design choices in the framework through multiple ablation studies. 

The goal ofprogrammatic Learning from Demonstration (LfD)is to learn a policy in a programming language that can be used to control a robot’s behavior from a set of user demonstrations. This paper presents a new programmatic LfD algorithm that targetslong-horizon robot taskswhich require synthesizing programs with complex control flow structures, including nested loops with multiple conditionals. Our proposed method first learns a program sketch that captures the target program’s control flow and then completes this sketch using an LLM-guided search procedure that incorporates a novel technique for proving unrealizability of programming-by-demonstration problems. We have implemented our approach in a new tool calledprolexand present the results of a comprehensive experimental evaluation on 120 benchmarks involving complex tasks and environments. We show that, given a 120 second time limit,prolexcan find a program consistent with the demonstrations in 80% of the cases. Furthermore, for 81% of the tasks for which a solution is returned,prolexis able to find the ground truth program with just one demonstration. In comparison, CVC5, a syntaxguided synthesis tool, is only able to solve 25% of the caseseven when given the ground truth program sketch, and an LLM-based approach, GPT-Synth, is unable to solve any of the tasks due to the environment complexity.