Zobrazeno 1 - 10
of 1 859
pro vyhledávání: '"P Sreenath"'
Autor:
Yue, Linzhu, Song, Zhitao, Dong, Jinhu, Li, Zhongyu, Zhang, Hongbo, Zhang, Lingwei, Zeng, Xuanqi, Sreenath, Koushil, Liu, Yun-hui
Natural terrain complexity often necessitates agile movements like jumping in animals to improve traversal efficiency. To enable similar capabilities in quadruped robots, complex real-time jumping maneuvers are required. Current research does not ade
Externí odkaz:
http://arxiv.org/abs/2411.04494
This paper introduces a framework for interactive navigation through adaptive non-prehensile mobile manipulation. A key challenge in this process is handling objects with unknown dynamics, which are difficult to infer from visual observation. To addr
Externí odkaz:
http://arxiv.org/abs/2410.13418
Autor:
Chen, Zixuan, He, Xialin, Wang, Yen-Jen, Liao, Qiayuan, Ze, Yanjie, Li, Zhongyu, Sastry, S. Shankar, Wu, Jiajun, Sreenath, Koushil, Gupta, Saurabh, Peng, Xue Bin
Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and sm
Externí odkaz:
http://arxiv.org/abs/2410.11825
Autor:
Zhang, Hongbo, Li, Zhongyu, Zeng, Xuanqi, Smith, Laura, Stachowicz, Kyle, Shah, Dhruv, Yue, Linzhu, Song, Zhitao, Xia, Weipeng, Levine, Sergey, Sreenath, Koushil, Liu, Yun-hui
The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing different terra
Externí odkaz:
http://arxiv.org/abs/2410.10621
Autor:
K, Roshna, Sreenath, V.
Observations by Planck indicate that CMB anisotropies are consistent with predictions of nearly Gaussian primordial perturbations as the one generated in slow-roll inflation. On the other hand, loop quantum cosmology (LQC) generates a non-Gaussian bi
Externí odkaz:
http://arxiv.org/abs/2410.00614
We propose simple quantitative criteria, based on counting statistics in resonant harmonic detectors, that probe the quantum mechanical character of radiation fields. They provide, in particular, practical means to test the null hypothesis that a giv
Externí odkaz:
http://arxiv.org/abs/2409.20378
Curriculum learning is a training mechanism in reinforcement learning (RL) that facilitates the achievement of complex policies by progressively increasing the task difficulty during training. However, designing effective curricula for a specific tas
Externí odkaz:
http://arxiv.org/abs/2409.18382
Autor:
Xia, Xingpeng, Choi, Jason J., Agrawal, Ayush, Sreenath, Koushil, Tomlin, Claire J., Bansal, Somil
Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine their effectiveness. In this work, we are interested in designing a le
Externí odkaz:
http://arxiv.org/abs/2409.16301
Safety is one of the fundamental challenges in control theory. Recently, multi-step optimal control problems for discrete-time dynamical systems were developed to ensure stability, while adhering to input constraints and safety-critical requirements.
Externí odkaz:
http://arxiv.org/abs/2409.08300
We introduce Berkeley Humanoid, a reliable and low-cost mid-scale humanoid research platform for learning-based control. Our lightweight, in-house-built robot is designed specifically for learning algorithms with low simulation complexity, anthropomo
Externí odkaz:
http://arxiv.org/abs/2407.21781