Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Banerjee, Somrita"'
Autor:
Foutter, Matthew, Bhoj, Praneet, Sinha, Rohan, Elhafsi, Amine, Banerjee, Somrita, Agia, Christopher, Kruger, Justin, Guffanti, Tommaso, Gammelli, Daniele, D'Amico, Simone, Pavone, Marco
Foundation models, e.g., large language models, possess attributes of intelligence which offer promise to endow a robot with the contextual understanding necessary to navigate complex, unstructured tasks in the wild. In the future of space robotics,
Externí odkaz:
http://arxiv.org/abs/2408.05924
Autor:
Hindy, Ali, Luo, Rachel, Banerjee, Somrita, Kuck, Jonathan, Schmerling, Edward, Pavone, Marco
Machine learning systems deployed in safety-critical robotics settings must be robust to distribution shifts. However, system designers must understand the cause of a distribution shift in order to implement the appropriate intervention or mitigation
Externí odkaz:
http://arxiv.org/abs/2407.21748
This work focuses on autonomous contingency planning for scientific missions by enabling rapid policy computation from any off-nominal point in the state space in the event of a delay or deviation from the nominal mission plan. Successful contingency
Externí odkaz:
http://arxiv.org/abs/2402.16342
Autor:
Sinha, Rohan, Sharma, Apoorva, Banerjee, Somrita, Lew, Thomas, Luo, Rachel, Richards, Spencer M., Sun, Yixiao, Schmerling, Edward, Pavone, Marco
When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important chall
Externí odkaz:
http://arxiv.org/abs/2212.14020
Autor:
Banerjee, Somrita, Sharma, Apoorva, Schmerling, Edward, Spolaor, Max, Nemerouf, Michael, Pavone, Marco
As input distributions evolve over a mission lifetime, maintaining performance of learning-based models becomes challenging. This paper presents a framework to incrementally retrain a model by selecting a subset of test inputs to label, which allows
Externí odkaz:
http://arxiv.org/abs/2209.06855
Utilization aware and network I/O intensive virtual machine placement policies for cloud data center
Publikováno v:
In Journal of Network and Computer Applications September 2022 205