(IEEE RA-L; Volume 10, Issue 6) Y. Lee, A. Li, P. Huang, E. Heiden, K. M. Jatavallabhula, F. Damken, K. Smith, D. Nowrouzezahrai, F. Ramos, F. Shkurti [ arXiv ] [ DOI ] [ Journal Issue ]
Abstract
Planning for sequential robotics tasks often requires integrated symbolic and geometric reasoning. TAMP algorithms typically solve these problems by performing a tree search over high-level task sequences while checking for kinematic and dynamic feasibility. This can be inefficient because, typically, candidate task plans resulting from the tree search ignore geometric information. This often leads to motion planning failures that require expensive backtracking steps to find alternative task plans. We propose a novel approach to TAMP called Stein Task and Motion Planning (STAMP) that relaxes the hybrid optimization problem into a continuous domain. This allows us to leverage gradients from differentiable physics simulation to fully optimize discrete and continuous plan parameters for TAMP. In particular, we solve the optimization problem using a gradient-based variational inference algorithm called Stein Variational Gradient Descent. This allows us to find a distribution of solutions within a single optimization run. Furthermore, we use an off-the-shelf differentiable physics simulator that is parallelized on the GPU to run parallelized inference over diverse plan parameters. We demonstrate our method on a variety of problems and show that it can find multiple diverse plans in a single optimization run while also being significantly faster than existing approaches.Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
(AIES 2024) K. Vida*, F. Damken*, A. Lauscher [ arXiv ] [ Code ] [ DOI ] [ Full Text PDF ] [ Proceedings ]
Abstract
Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people’s decisions or opinions through their daily use. Therefore, understanding how and which moral judgements these LLMs make is crucial. However, morality is not universal and depends on the cultural background. This raises the question of whether these cultural preferences are also reflected in LLMs when prompted in different languages or whether moral decision-making is consistent across different languages. So far, most research has focused on investigating the inherent values of LLMs in English. While a few works conduct multilingual analyses of moral bias in LLMs in a multilingual setting, these analyses do not go beyond atomic actions. To the best of our knowledge, a multilingual analysis of moral bias in dilemmas has not yet been conducted.
To address this, our paper builds on the moral machine experiment (MME) to investigate the moral preferences of five LLMs, Falcon, Gemini, Llama, GPT, and MPT, in a multilingual setting and compares them with the preferences collected from humans belonging to different cultures. To accomplish this, we generate 6500 scenarios of the MME and prompt the models in ten languages on which action to take. Our analysis reveals that all LLMs inhibit different moral biases to some degree and that they not only differ from the human preferences but also across multiple languages within the models themselves. Moreover, we find that almost all models, particularly Llama 3, divert greatly from human values and, for instance, prefer saving fewer people over saving more.
STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent
(CoRL 2023: LEAP Workshop) Y. Lee, P. Huang, K. M. Jatavallabhula, A. Li, F. Damken, E. Heiden, K. Smith, D. Nowrouzezahrai, F. Ramos, F. Shkurti [ arXiv ] [ Full Text PDF ] [ OpenReview ]