As a result, the agent may take a very long time to perceive the environment due to limited camera scope. In contrast, humans typically gain a larger field of view by looking around for a better perception of the environment.

A Los Angeles police lieutenant has filed a legal claim against the city, alleging his superiors ignored his warnings about misconduct in an anti-gang unit until it became a public scandal, leading to him facing termination. The claim, which typically serves as the precursor to a lawsuit, was brought this month by Lt. Mark Garza. It's the first litigation being pursued by a former member the Mission Division gang unit, whose officers came under investigation last year over allegations they illegally stopped and searched vehicles and stole from people they pulled over. Garza, who was in charge of the unit, said he reported his suspicion in June 2023 that some of his officers were conducting "ghost stops," which meant their actions could go unnoticed because they didn't document the encounters or turn on their body-worn or dashboard cameras and never informed police dispatch of where they were. At that time, Garza said, the department's body camera policy required supervisors to review only footage related to "complaints, use of force and pursuits."

The Los Angeles Police Department is considering changing department policy to increase random reviews of body camera recordings that don't involve arrests or the use of force, according to an email from Chief Michel Moore to his senior staff. Moore wrote that "it's in our best interest to strengthen and reinforce" the number of incidents involving patrol and gang officers that are reviewed roughly every 30 days, "which more closely aligns with other agencies." "Additionally, I support expanding the incidents that qualify beyond those in which no enforcement action was taken," Moore said in the Oct. 19 email, a copy of which was reviewed by The Times. Internal LAPD reports indicate the problem of police officers flouting department body camera policy is more widespread than officials have been telling the public. Moore's directive comes months after revelations that members of a scandal-ridden gang unit were routinely turning off their body-worn cameras in violation of department policy.

Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently with camera sensors only. Existing navigation methods mainly focus on fixed cameras and few attempts have been made to navigate with active cameras. As a result, the agent may take a very long time to perceive the environment due to limited camera scope. In contrast, humans typically gain a larger field of view by looking around for a better perception of the environment. How to make robots perceive the environment as efficiently as humans is a fundamental problem in robotics. In this paper, we consider navigating to multiple objects more efficiently with active cameras. Specifically, we cast moving camera to a Markov Decision Process and reformulate the active camera problem as a reinforcement learning problem. However, we have to address two new challenges: 1) how to learn a good camera policy in complex environments and 2) how to coordinate it with the navigation policy. To address these, we carefully design a reward function to encourage the agent to explore more areas by moving camera actively. Moreover, we exploit human experience to infer a rule-based camera action to guide the learning process. Last, to better coordinate two kinds of policies, the camera policy takes navigation actions into account when making camera moving decisions. Experimental results show our camera policy consistently improves the performance of multi-object navigation over four baselines on two datasets.