BEHAVIOR-1K: A Benchmark for Embodied AI with 1, 000 Everyday Activities and Realistic Simulation

By Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Siddharth Srivastava, Roberto Mart'in-Mart'in, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun and 18 more. Conference on Robot Learning, 2022

370 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/69764fcc646e4c608ac08eeb4c784cf8465268d2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yilun Du
2. Chuang Gan
3. Josh Tenenbaum
4. Sergey Levine
5. Abhinav Kumar Gupta
6. Li Fei-Fei
7. Yoshua Bengio
8. Andrea Vedaldi

Citations in the corpus

• ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation (2024, methodology): “We additionally implement ReKep in OmniGibson [153] for the Pour Tea task.”
• Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, unknown): “The model integrates multimodal LLMs with vision-based robotic grasping frameworks to generate grasps based on semantics and vision.”
• RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots (2024, methodology): “RoboCasa is one of the few frameworks to feature photorealistic rendering [21, 40, 27, 10, 6] and multiple robot embodiments [21, 26, 27, 6, 34].”
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models (2023, unknown): “The learned cost functions are then used by reinforcement learning [111, 108, 116], imitation learning [106, 105], or trajectory optimization [104, 35] to generate robot actions.”
• Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “…Pallagani et al., 2022; Gramopadhye & Szafir, 2022; Yuan et al., 2023; Li et al., 2022; Wang et al., 2023d), especially in embodied environments (Li et al., 2023a; Padmakumar et al., 2022; Kolve et al., 2017; Shridhar et al., 2020; Misra et al., 2018; Zhu et al., 2017; Brodeur et al., 2017; Xia…”
• ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills (2023, background): “Since BEHAVIOR-1K (Li et al., 2022) is not public yet, some detailed information is unknown.”
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning (2023, unknown): “Robot Learning Benchmarks A variety of robot learning benchmarks have been proposed to address challenges in meta learning (MetaWorld [73]), causality learning (CausalWorld [1]), multi-task learning [27, 35], policy generalization to unseen objects [47, 24], and compositional learning [44].”
• MimicPlay: Long-Horizon Imitation Learning by Watching Human Play (2023, methodology): “We choose LIBERO due to its utilization of the BDDL language [63] for goal specification, which facilitates the multitask evaluation for learning from play data.”
• Foundation models in robotics: Applications, challenges, and the future (2023, unknown): “To bridge the gap between simulation and real-world, iGibson [146] and BEHAVIOR-1K [207] further support the simulation of a more diverse set of household tasks and reach high levels of simulation realism.”