More Like this

1. Extending rational models of communication from beliefs to actions

   Sumers, T.; Hawkins, R.D.; Ho, M.; Griffiths, T.L. (January 2021, Proceedings of the Annual Conference of the Cognitive Science Society)

   null (Ed.)

   Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or integrate them. Indeed, we find that they are conflated in standard referential communication tasks. To distinguish these accounts, we introduce a new paradigm called signaling bandits, generalizing classic Lewis signaling games to a multi-armed bandit setting where all targets in the context have some relative value. We develop three speaker models: a belief-oriented speaker with a purely informative objective; an action-oriented speaker with an instrumental objective; and a combined speaker which integrates the two by inducing listener beliefs that generally lead to desirable actions. We then present a series of simulations demonstrating that grounding production choices in future listener actions results in relevance effects and flexible uses of nonliteral language. More broadly, our findings suggest that language games based on richer decision problems are a promising avenue for insight into rational communication. 

   more » « less
2. Leveraging symmetries in pick and place

   https://doi.org/10.1177/02783649231225775  

   Huang, Haojie; Wang, Dian; Tangri, Arsh; Walters, Robin; Platt, Robert (January 2024, The International Journal of Robotics Research)

   Robotic pick and place tasks are symmetric under translations and rotations of both the object to be picked and the desired place pose. For example, if the pick object is rotated or translated, then the optimal pick action should also rotate or translate. The same is true for the place pose; if the desired place pose changes, then the place action should also transform accordingly. A recently proposed pick and place framework known as Transporter Net (Zeng, Florence, Tompson, Welker, Chien, Attarian, Armstrong, Krasin, Duong, Sindhwani et al., 2021) captures some of these symmetries, but not all. This paper analytically studies the symmetries present in planar robotic pick and place and proposes a method of incorporating equivariant neural models into Transporter Net in a way that captures all symmetries. The new model, which we call Equivariant Transporter Net, is equivariant to both pick and place symmetries and can immediately generalize pick and place knowledge to different pick and place poses. We evaluate the new model empirically and show that it is much more sample-efficient than the non-symmetric version, resulting in a system that can imitate demonstrated pick and place behavior using very few human demonstrations on a variety of imitation learning tasks. 

   more » « less
3. Efficient Symbolic Reactive Synthesis for Finite-Horizon Tasks

   He, Keliang; Wells, Andrew; Kavraki, Lydia E; Vardi, Moshe Y. (April 2019, 2019 International Conference on Robotics and Automation)

   When humans and robots perform complex tasks together, the robot must have a strategy to choose its actions based on observed human behavior. One well-studied approach for finding such strategies is reactive synthesis. Existing approaches for finite-horizon tasks have used an explicit state approach, which incurs high runtime. In this work, we present a compositional approach to perform synthesis for finite-horizon tasks based on binary decision diagrams. We show that for pick-and-place tasks, the compositional approach achieves orders-of-magnitude speed-ups compared to previous approaches. We demonstrate the synthesized strategy on a UR5 robot. 

   more » « less
4. Visual Robot Task Planning

   Chris Paxton, Yotam Barnoy (July 2018, WORKSHOP ON LEARNING FROM DEMONSTRATIONS FOR HIGH LEVEL ROBOTIC TASKS, AT ROBOTICS SCIENCE AND SYSTEMS)

   Prospection, the act of predicting the consequences of many possible futures, is intrinsic to human planning and action, and may even be at the root of consciousness. Surprisingly, this idea has been explored comparatively little in robotics. In this work, we propose a neural network architecture and associated planning algorithm that (1) learns a representation of the world useful for generating prospective futures after the application of high-level actions from a large pool of expert demonstrations, (2) uses this generative model to simulate the result of sequences of high-level actions in a variety of environments, and (3) uses this same representation to evaluate these actions and perform tree search to find a sequence of high-level actions in a new environment. Models are trained via imitation learning on a variety of domains, including navigation, pick-and-place, and a surgical robotics task. Our approach allows us to visualize intermediate motion goals and learn to plan complex activity from visual information. 

   more » « less
5. SPRI: Aligning Large Language Models with Context-Situated Principles

   Zhan, Hongli; Azmat, Muneeza; Horesh, Raya; Li, Junyi Jessy; Yurochkin, Mikhail (July 2025, Proceedings of the Forty-Second International Conference on Machine Learning (ICML 2025))

   Aligning Large Language Models to integrate and reflect human values, especially for tasks that demand intricate human oversight, is arduous since it is resource-intensive and time-consuming to depend on human expertise for context-specific guidance. Prior work has utilized predefined sets of rules or principles to steer the behavior of models (Bai et al., 2022; Sun et al., 2023). However, these principles tend to be generic, making it challenging to adapt them to each individual input query or context. In this work, we present Situated-PRInciples (SPRI), a framework requiring minimal or no human effort that is designed to automatically generate guiding principles in real-time for each input query and utilize them to align each response. We evaluate SPRI on three tasks, and show that 1) SPRI can derive principles in a complex domain-specific task that leads to on-par performance as expert-crafted ones; 2) SPRI-generated principles lead to instance-specific rubrics that outperform prior LLM-as-a-judge frameworks; 3) using SPRI to generate synthetic SFT data leads to substantial improvement on truthfulness. 

   more » « less