13 June 2024 in IEEE Robotics & Automation Magazine
Queer individuals face significant obstacles in the fields of science, technology, engineering, mathematics (STEM), and computing, including high levels of harassment and professional limitations [1] , but only some of these STEM fields have been recently promoting the integration and welcoming of people with queer identities to increase representation and inclusion. ( Queer is used here as an umbrella term for those who do not identify as heterosexual or cisgender, often labeled the LGBTQIA+ community.) This situation drove the creation of organizations like Queer in Artificial Intelligence (AI) and Queer in Human–Computer Interaction (HCI) that study and monitor the inclusion of queer people and provide safe and welcoming spaces within their respective scientific communities. Initial studies performed by these organizations found areas for their fields to improve. Queer in HCI studies indicated that queer people face significant pressures and barriers not experienced by all HCI researchers [2] . Queer in AI demographic surveys showed that 67% of the group’s members faced at least one safety incident in 2021, 79.9% of its members reported mental health issues that impaired their ability to conduct research, and 77.4% of its members struggled with a lack of community that they could rely on [3] . Other challenges include inaccessibility to conferences, due to local discrimination toward queer people; lack of tailored academic support; inflexible name change policies; and lack of representation [4] . Both Queer in AI and Queer in HCI have shed light on these issues while increasing the level of involvement and feeling of belonging of the queer communities in their respective research fields, benefits that we would like to see extended to the robotics community.
1 August 2007 in Blood Reviews
1 March 2025 in The International Journal of Robotics Research
Joint estimation of grasped object pose and extrinsic contacts is central to robust and dexterous manipulation. In this paper, we introduce MultiSCOPE, a state-estimation algorithm that leverages sequential frictional contacts (e.g., pokes) to jointly estimate contact locations and grasped object poses using exclusively proprioception and tactile feedback. Our method addresses the problem of reducing object pose uncertainty by using two complementary particle filters over a series of actions: one to estimate contact location (CPFGrasp) and another to estimate object poses (SCOPE). Our method addresses uncertainty in both robot proprioception and force-torque measurements, which is important for estimating in-hand object pose in the real world. We implement and evaluate our approach on simulated and real-world single-arm and dual-arm robotic systems. We demonstrate that by bringing two objects into contact several times, the robots can infer contact location and object poses simultaneously.