David D. Fan

David D. Fan, Evangelos A. Theodorou

Trajectory optimization considers the problem of deciding how to control a dynamical system to move along a trajectory which minimizes some cost function. Differential Dynamic Programming (DDP) is an optimal control method which utilizes a second-order approximation of the problem to find the control. It is fast enough to allow real-time control and has been shown to work well for trajectory optimization in robotic systems. Here we extend classic DDP to systems with multiple time-delays in the state. Being able to find optimal trajectories for time-delayed systems with DDP opens up the possibility to use richer models for system identification and control, including recurrent neural networks with multiple timesteps in the state. We demonstrate the algorithm on a two-tank continuous stirred tank reactor. We also demonstrate the algorithm on a recurrent neural network trained to model an inverted pendulum with position information only.

Muhammad Fadhil Ginting, Dong-Ki Kim, Xiangyun Meng et al.

As robots become increasingly capable of operating over extended periods -- spanning days, weeks, and even months -- they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Question Answering (LA-EQA), a new task in which a robot must both recall past experiences and actively explore its environment to answer complex, temporally-grounded questions. Unlike traditional EQA settings, which typically focus either on understanding the present environment alone or on recalling a single past observation, LA-EQA challenges an agent to reason over past, present, and possible future states, deciding when to explore, when to consult its memory, and when to stop gathering observations and provide a final answer. Standard EQA approaches based on large models struggle in this setting due to limited context windows, absence of persistent memory, and an inability to combine memory recall with active exploration. To address this, we propose a structured memory system for robots, inspired by the mind palace method from cognitive science. Our method encodes episodic experiences as scene-graph-based world instances, forming a reasoning and planning algorithm that enables targeted memory retrieval and guided navigation. To balance the exploration-recall trade-off, we introduce value-of-information-based stopping criteria that determines when the agent has gathered sufficient information. We evaluate our method on real-world experiments and introduce a new benchmark that spans popular simulation environments and actual industrial sites. Our approach significantly outperforms state-of-the-art baselines, yielding substantial gains in both answer accuracy and exploration efficiency.

David D. Fan, Sharmita Dey, Ali-akbar Agha-mohammadi et al.

One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move. A significant source of difficulty in this determination arises from stochasticity and uncertainty, coming from localization error, sensor sparsity and noise, difficult-to-model robot-ground interactions, and disturbances to the motion of the vehicle. Classical approaches to this problem rely on geometric analysis of the surrounding terrain, which can be prone to modeling errors and can be computationally expensive. Moreover, modeling the distribution of uncertain traversability costs is a difficult task, compounded by the various error sources mentioned above. In this work, we take a principled learning approach to this problem. We introduce a neural network architecture for robustly learning the distribution of traversability costs. Because we are motivated by preserving the life of the robot, we tackle this learning problem from the perspective of learning tail-risks, i.e. the Conditional Value-at-Risk (CVaR). We show that this approach reliably learns the expected tail risk given a desired probability risk threshold between 0 and 1, producing a traversability costmap which is more robust to outliers, more accurately captures tail risks, and is more computationally efficient, when compared against baselines. We validate our method on data collected a legged robot navigating challenging, unstructured environments including an abandoned subway, limestone caves, and lava tube caves.

Ali Agha, Kyohei Otsu, Benjamin Morrell et al.

This paper presents and discusses algorithms, hardware, and software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in the DARPA Subterranean Challenge. Specifically, it presents the techniques utilized within the Tunnel (2019) and Urban (2020) competitions, where CoSTAR achieved 2nd and 1st place, respectively. We also discuss CoSTAR's demonstrations in Martian-analog surface and subsurface (lava tubes) exploration. The paper introduces our autonomy solution, referred to as NeBula (Networked Belief-aware Perceptual Autonomy). NeBula is an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states). We discuss various components of the NeBula framework, including: (i) geometric and semantic environment mapping; (ii) a multi-modal positioning system; (iii) traversability analysis and local planning; (iv) global motion planning and exploration behavior; (i) risk-aware mission planning; (vi) networking and decentralized reasoning; and (vii) learning-enabled adaptation. We discuss the performance of NeBula on several robot types (e.g. wheeled, legged, flying), in various environments. We discuss the specific results and lessons learned from fielding this solution in the challenging courses of the DARPA Subterranean Challenge competition.

David D. Fan, Kyohei Otsu, Yuki Kubo et al.

Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertainty-aware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an abandoned subway and an underground lava tube.

Sung-Kyun Kim, Amanda Bouman, Gautam Salhotra et al.

In order for an autonomous robot to efficiently explore an unknown environment, it must account for uncertainty in sensor measurements, hazard assessment, localization, and motion execution. Making decisions for maximal reward in a stochastic setting requires value learning and policy construction over a belief space, i.e., probability distribution over all possible robot-world states. However, belief space planning in a large spatial environment over long temporal horizons suffers from severe computational challenges. Moreover, constructed policies must safely adapt to unexpected changes in the belief at runtime. This work proposes a scalable value learning framework, PLGRIM (Probabilistic Local and Global Reasoning on Information roadMaps), that bridges the gap between (i) local, risk-aware resiliency and (ii) global, reward-seeking mission objectives. Leveraging hierarchical belief space planners with information-rich graph structures, PLGRIM addresses large-scale exploration problems while providing locally near-optimal coverage plans. We validate our proposed framework with high-fidelity dynamic simulations in diverse environments and on physical robots in Martian-analog lava tubes.

Rohan Thakker, Nikhilesh Alatur, David D. Fan et al.

We propose a framework for resilient autonomous navigation in perceptually challenging unknown environments with mobility-stressing elements such as uneven surfaces with rocks and boulders, steep slopes, negative obstacles like cliffs and holes, and narrow passages. Environments are GPS-denied and perceptually-degraded with variable lighting from dark to lit and obscurants (dust, fog, smoke). Lack of prior maps and degraded communication eliminates the possibility of prior or off-board computation or operator intervention. This necessitates real-time on-board computation using noisy sensor data. To address these challenges, we propose a resilient architecture that exploits redundancy and heterogeneity in sensing modalities. Further resilience is achieved by triggering recovery behaviors upon failure. We propose a fast settling algorithm to generate robust multi-fidelity traversability estimates in real-time. The proposed approach was deployed on multiple physical systems including skid-steer and tracked robots, a high-speed RC car and legged robots, as a part of Team CoSTAR's effort to the DARPA Subterranean Challenge, where the team won 2nd and 1st place in the Tunnel and Urban Circuits, respectively.

Amanda Bouman, Muhammad Fadhil Ginting, Nikhilesh Alatur et al.

This paper serves as one of the first efforts to enable large-scale and long-duration autonomy using the Boston Dynamics Spot robot. Motivated by exploring extreme environments, particularly those involved in the DARPA Subterranean Challenge, this paper pushes the boundaries of the state-of-practice in enabling legged robotic systems to accomplish real-world complex missions in relevant scenarios. In particular, we discuss the behaviors and capabilities which emerge from the integration of the autonomy architecture NeBula (Networked Belief-aware Perceptual Autonomy) with next-generation mobility systems. We will discuss the hardware and software challenges, and solutions in mobility, perception, autonomy, and very briefly, wireless networking, as well as lessons learned and future directions. We demonstrate the performance of the proposed solutions on physical systems in real-world scenarios.

David D. Fan, Rohan Thakker, Tara Bartlett et al.

Hybrid ground and aerial vehicles can possess distinct advantages over ground-only or flight-only designs in terms of energy savings and increased mobility. In this work we outline our unified framework for controls, planning, and autonomy of hybrid ground/air vehicles. Our contribution is three-fold: 1) We develop a control scheme for the control of passive two-wheeled hybrid ground/aerial vehicles. 2) We present a unified planner for both rolling and flying by leveraging differential flatness mappings. 3) We conduct experiments leveraging mapping and global planning for hybrid mobility in unknown environments, showing that hybrid mobility uses up to five times less energy than flying only.

Angel Santamaria-Navarro, Rohan Thakker, David D. Fan et al.

Robots and particularly drones are especially useful in exploring extreme environments that pose hazards to humans. To ensure safe operations in these situations, usually perceptually degraded and without good GNSS, it is critical to have a reliable and robust state estimation solution. The main body of literature in robot state estimation focuses on developing complex algorithms favoring accuracy. Typically, these approaches rely on a strong underlying assumption: the main estimation engine will not fail during operation. In contrast, we propose an architecture that pursues robustness in state estimation by considering redundancy and heterogeneity in both sensing and estimation algorithms. The architecture is designed to expect and detect failures and adapt the behavior of the system to ensure safety. To this end, we present HeRO (Heterogeneous Redundant Odometry): a stack of estimation algorithms running in parallel supervised by a resiliency logic. This logic carries out three main functions: a) perform confidence tests both in data quality and algorithm health; b) re-initialize those algorithms that might be malfunctioning; c) generate a smooth state estimate by multiplexing the inputs based on their quality. The state and quality estimates are used by the guidance and control modules to adapt the mobility behaviors of the system. The validation and utility of the approach are shown with real experiments on a flying robot for the use case of autonomous exploration of subterranean environments, with particular results from the STIX event of the DARPA Subterranean Challenge.

David D. Fan, Ali-akbar Agha-mohammadi, Evangelos A. Theodorou

Learning-based control aims to construct models of a system to use for planning or trajectory optimization, e.g. in model-based reinforcement learning. In order to obtain guarantees of safety in this context, uncertainty must be accurately quantified. This uncertainty may come from errors in learning (due to a lack of data, for example), or may be inherent to the system. Propagating uncertainty forward in learned dynamics models is a difficult problem. In this work we use deep learning to obtain expressive and flexible models of how distributions of trajectories behave, which we then use for nonlinear Model Predictive Control (MPC). We introduce a deep quantile regression framework for control that enforces probabilistic quantile bounds and quantifies epistemic uncertainty. Using our method we explore three different approaches for learning tubes that contain the possible trajectories of the system, and demonstrate how to use each of them in a Tube MPC scheme. We prove these schemes are recursively feasible and satisfy constraints with a desired margin of probability. We present experiments in simulation on a nonlinear quadrotor system, demonstrating the practical efficacy of these ideas.

David D. Fan, Jennifer Nguyen, Rohan Thakker et al.

Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical systems, which have constraints on safety, stability, and real-time performance. We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties. Central to our method is the use of Bayesian model learning, which provides an avenue for maintaining appropriate degrees of caution in the face of the unknown. In the proposed approach, we develop an adaptive control framework leveraging the theory of stochastic CLFs (Control Lyapunov Functions) and stochastic CBFs (Control Barrier Functions) along with tractable Bayesian model learning via Gaussian Processes or Bayesian neural networks. Under reasonable assumptions, we guarantee stability and safety while adapting to unknown dynamics with probability 1. We demonstrate this architecture for high-speed terrestrial mobility targeting potential applications in safety-critical high-speed Mars rover missions.

Thomas Lew, Tomoki Emmei, David D. Fan et al.

Autonomous exploration of unknown environments with aerial vehicles remains a challenge, especially in perceptually degraded conditions. Dust, fog, or a lack of visual or LiDAR-based features results in severe difficulties for state estimation algorithms, which failure can be catastrophic. In this work, we show that it is indeed possible to navigate in such conditions without any exteroceptive sensing by exploiting collisions instead of treating them as constraints. To this end, we present a novel contact-based inertial odometry (CIO) algorithm: it uses estimated external forces with the environment to detect collisions and generate pseudo-measurements of the robot velocity, enabling autonomous flight. To fully exploit this method, we first perform modeling of a hybrid ground and aerial vehicle which can withstand collisions at moderate speeds, for which we develop an external wrench estimation algorithm. Then, we present our CIO algorithm and develop a reactive planner and control law which encourage exploration by bouncing off obstacles. All components of this framework are validated in hardware experiments and we demonstrate that a quadrotor can traverse a cluttered environment using an IMU only. This work can be used on drones to recover from visual inertial odometry failure or on micro-drones that do not have the payload capacity to carry cameras, LiDARs or powerful computers.

Marcus Pereira, David D. Fan, Gabriel Nakajima An et al.

In this paper we investigate the use of MPC-inspired neural network policies for sequential decision making. We introduce an extension to the DAgger algorithm for training such policies and show how they have improved training performance and generalization capabilities. We take advantage of this extension to show scalable and efficient training of complex planning policy architectures in continuous state and action spaces. We provide an extensive comparison of neural network policies by considering feed forward policies, recurrent policies, and recurrent policies with planning structure inspired by the Path Integral control framework. Our results suggest that MPC-type recurrent policies have better robustness to disturbances and modeling error.