Latent safety filters extend Hamilton-Jacobi (HJ) reachability to operate on latent state representations and dynamics learned directly from high-dimensional observations, enabling safe visuo-motor control under hard-to-model constraints. However, existing methods implement "least-restrictive" filtering that discretely switch between nominal and safety policies, potentially undermining the task performance that makes modern visuomotor policies valuable. While reach-ability value functions can, in principle, be adapted to be control barrier functions (CBFs) for smooth optimization-based filtering, we theoretically and empirically show that current latent-space learning methods produce fundamentally incompatible value functions. We identify two sources of incompatibility: First, in HJ reachability, failures are encoded via a "margin function" in latent space, whose sign indicates whether or not a latent is in the constraint set. However, representing the margin function as a classifier yields saturated value functions that exhibit discontinuous jumps. We prove that the value function's Lipschitz constant scales linearly with the margin function's Lipschitz constant, revealing that smooth CBFs require smooth margins. Second, reinforcement learning (RL) approximations trained solely on safety policy data yield inaccurate value estimates for nominal policy actions, precisely where CBF filtering needs them. We propose the LatentCBF, which addresses both challenges through gradient penalties that lead to smooth margin functions without additional labeling, and a value-training procedure that mixes data from both nominal and safety policy distributions. Experiments on simulated benchmarks and hardware with a vision-based manipulation policy demonstrate that LatentCBF enables smooth safety filtering while doubling the task-completion rate over prior switching methods.

Autonomous vehicles (AVs) are becoming increasingly popular, with their applications now extending beyond just a mode of transportation to serving as mobile actuators of a traffic flow to control flow dynamics. This contrasts with traditional fixed-location actuators, such as traffic signals, and is referred to as Lagrangian traffic control. However, designing effective Lagrangian traffic control policies for AVs that generalize across traffic scenarios introduces a major challenge. Real-world traffic environments are highly diverse, and developing policies that perform robustly across such diverse traffic scenarios is challenging. It is further compounded by the joint complexity of the multi-agent nature of traffic systems, mixed motives among participants, and conflicting optimization objectives subject to strict physical and external constraints. To address these challenges, we introduce Multi-Residual Mixture of Expert Learning (MRMEL), a novel framework for Lagrangian traffic control that augments a given suboptimal nominal policy with a learned residual while explicitly accounting for the structure of the traffic scenario space. In particular, taking inspiration from residual reinforcement learning, MRMEL augments a suboptimal nominal AV control policy by learning a residual correction, but at the same time dynamically selects the most suitable nominal policy from a pool of nominal policies conditioned on the traffic scenarios and modeled as a mixture of experts. We validate MRMEL using a case study in cooperative eco-driving at signalized intersections in Atlanta, Dallas Fort Worth, and Salt Lake City, with real-world data-driven traffic scenarios. The results show that MRMEL consistently yields superior performance-achieving an additional 4%-9% reduction in aggregate vehicle emissions relative to the strongest baseline in each setting.

-- Throwing is a fundamental skill that enables robots to manipulate objects in ways that extend beyond the reach of their arms. We present a control framework that combines learning and model-based control for prehensile whole-body throwing with legged mobile manipulators. Our framework consists of three components: a nominal tracking policy for the end-effector, a high-frequency residual policy to enhance tracking accuracy, and an optimization-based module to improve end-effector acceleration control. The proposed controller achieved the average of 0.28 m landing error when throwing at targets located 6 m away. Furthermore, in a comparative study with university students, the system achieved a velocity tracking error of 0.398 m/s and a success rate of 56.8%, hitting small targets randomly placed at distances of 3-5 m while throwing at a specified speed of 6 m/s. In contrast, humans have a success rate of only 15.2%. This work provides an early demonstration of prehensile throwing with quantified accuracy on hardware, contributing to progress in dynamic whole-body manipulation. A video summarizing the proposed method and the hardware tests is available at https://youtu.be/3ysgbN6Ca8A. Legged robots capable of performing whole-body dynamic and high-precision manipulation tasks are essential for advancing applications such as delivery automation, disaster response, and dynamic object handling.

As learning-based methods for legged robots rapidly grow in popularity, it is important that we can provide safety assurances efficiently across different controllers and environments. Existing works either rely on a priori knowledge of the environment and safety constraints to ensure system safety or provide assurances for a specific locomotion policy. To address these limitations, we propose an observation-conditioned reachability-based (OCR) safety-filter framework. Our key idea is to use an OCR value network (OCR-VN) that predicts the optimal control-theoretic safety value function for new failure regions and dynamic uncertainty during deployment time. Specifically, the OCR-VN facilitates rapid safety adaptation through two key components: a LiDAR-based input that allows the dynamic construction of safe regions in light of new obstacles and a disturbance estimation module that accounts for dynamics uncertainty in the wild. The predicted safety value function is used to construct an adaptive safety filter that overrides the nominal quadruped controller when necessary to maintain safety. Through simulation studies and hardware experiments on a Unitree Go1 quadruped, we demonstrate that the proposed framework can automatically safeguard a wide range of hierarchical quadruped controllers, adapts to novel environments, and is robust to unmodeled dynamics without a priori access to the controllers or environments - hence, "One Filter to Deploy Them All". The experiment videos can be found on the project website.

Model-based planners and controllers are commonly used to solve complex manipulation problems as they can efficiently optimize diverse objectives and generalize to long horizon tasks. However, they are limited by the fidelity of their model which oftentimes leads to failures during deployment. To enable a robot to recover from such failures, we propose to use hierarchical reinforcement learning to learn a separate recovery policy. The recovery policy is triggered when a failure is detected based on sensory observations and seeks to take the robot to a state from which it can complete the task using the nominal model-based controllers. Our approach, called RecoveryChaining, uses a hybrid action space, where the model-based controllers are provided as additional \emph{nominal} options which allows the recovery policy to decide how to recover, when to switch to a nominal controller and which controller to switch to even with \emph{sparse rewards}. We evaluate our approach in three multi-step manipulation tasks with sparse rewards, where it learns significantly more robust recovery policies than those learned by baselines. Finally, we successfully transfer recovery policies learned in simulation to a physical robot to demonstrate the feasibility of sim-to-real transfer with our method.

Conventional control, such as model-based control, is commonly utilized in autonomous driving due to its efficiency and reliability. However, real-world autonomous driving contends with a multitude of diverse traffic scenarios that are challenging for these planning algorithms. Model-free Deep Reinforcement Learning (DRL) presents a promising avenue in this direction, but learning DRL control policies that generalize to multiple traffic scenarios is still a challenge. To address this, we introduce Multi-residual Task Learning (MRTL), a generic learning framework based on multi-task learning that, for a set of task scenarios, decomposes the control into nominal components that are effectively solved by conventional control methods and residual terms which are solved using learning. We employ MRTL for fleet-level emission reduction in mixed traffic using autonomous vehicles as a means of system control. By analyzing the performance of MRTL across nearly 600 signalized intersections and 1200 traffic scenarios, we demonstrate that it emerges as a promising approach to synergize the strengths of DRL and conventional methods in generalizable control.

Control barrier functions (CBF) have become popular as a safety filter to guarantee the safety of nonlinear dynamical systems for arbitrary inputs. However, it is difficult to construct functions that satisfy the CBF constraints for high relative degree systems with input constraints. To address these challenges, recent work has explored learning CBFs using neural networks via neural CBF (NCBF). However, such methods face difficulties when scaling to higher dimensional systems under input constraints. In this work, we first identify challenges that NCBFs face during training. Next, to address these challenges, we propose policy neural CBF (PNCBF), a method of constructing CBFs by learning the value function of a nominal policy, and show that the value function of the maximum-over-time cost is a CBF. We demonstrate the effectiveness of our method in simulation on a variety of systems ranging from toy linear systems to an F-16 jet with a 16-dimensional state space. Finally, we validate our approach on a two-agent quadcopter system on hardware under tight input constraints.

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments have implicit constraints that are difficult to specify and transfer to a learning agent. To address this challenge, we propose a novel method that utilizes the principle of maximum causal entropy to learn constraints and an optimal policy that adheres to these constraints, using demonstrations of agents that abide by the constraints. We prove convergence in a tabular setting and provide an approximation which scales to complex environments. We evaluate the effectiveness of the learned policy by assessing the reward received and the number of constraint violations, and we evaluate the learned cost function based on its transferability to other agents. Our method has been shown to outperform state-of-the-art approaches across a variety of tasks and environments, and it is able to handle problems with stochastic dynamics and a continuous state-action space.