This paper addresses the challenge of autonomous excavation of challenging terrains, in particular those that are prone to jamming and inter-particle adhesion when tackled by a standard penetrate-drag-scoop motion pattern. Inspired by human excavation strategies, our approach incorporates oscillatory rotation elements - including swivel, twist, and dive motions - to break up compacted, tangled grains and reduce jamming. We also present an adaptive impedance control method, the Reactive Attractor Impedance Controller (RAIC), that adapts a motion trajectory to unexpected forces during loading in a manner that tracks a trajectory closely when loads are low, but avoids excessive loads when significant resistance is met. Our method is evaluated on four terrains using a robotic arm, demonstrating improved excavation performance across multiple metrics, including volume scooped, protective stop rate, and trajectory completion percentage.

Predicting the near-term behavior of a reactive agent is crucial in many robotic scenarios, yet remains challenging when observations of that agent are sparse or intermittent. Vision-Language Models (VLMs) offer a promising avenue by integrating textual domain knowledge with visual cues, but their one-shot predictions often miss important edge cases and unusual maneuvers. Our key insight is that iterative, counterfactual exploration–where a dedicated module probes each proposed behavior hypothesis, explicitly represented as a plausible trajectory, for overlooked possibilities–can significantly enhance VLM-based behavioral forecasting. We present TRACE (Tree-of-thought Reasoning And Counterfactual Exploration), an inference framework that couples tree-of-thought generation with domain-aware feedback to refine behavior hypotheses over multiple rounds. Concretely, a VLM first proposes candidate trajectories for the agent; a counterfactual critic then suggests edge-case variations consistent with partial observations, prompting the VLM to expand or adjust its hypotheses in the next iteration. This creates a self-improving cycle where the VLM progressively internalizes edge cases from previous rounds, systematically uncovering not only typical behaviors but also rare or borderline maneuvers, ultimately yielding more robust trajectory predictions from minimal sensor data. We validate TRACE on both ground-vehicle simulations and real-world marine autonomous surface vehicles. Experimental results show that our method consistently outperforms standard VLM-driven and purely model-based baselines, capturing a broader range of feasible agent behaviors despite sparse sensing. Evaluation videos and code are available at trace-robotics.github.io.

Autonomous motion planning under unknown nonlinear dynamics presents significant challenges. An agent needs to continuously explore the system dynamics to acquire its properties, such as reachability, in order to guide system navigation adaptively. In this paper, we propose a hybrid planning-control framework designed to compute a feasible trajectory toward a target. Our approach involves partitioning the state space and approximating the system by a piecewise affine (PWA) system with constrained control inputs. By abstracting the PWA system into a directed weighted graph, we incrementally update the existence of its edges via affine system identification and reach control theory, introducing a predictive reachability condition by exploiting prior information of the unknown dynamics. Heuristic weights are assigned to edges based on whether their existence is certain or remains indeterminate. Consequently, we propose a framework that adaptively collects and analyzes data during mission execution, continually updates the predictive graph, and synthesizes a controller online based on the graph search outcomes. We demonstrate the efficacy of our approach through simulation scenarios involving a mobile robot operating in unknown terrains, with its unknown dynamics abstracted as a single integrator model.

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system’s optimal decision making strategy for mission completion. To model such environments, our work combines the previous notion of Time-Varying Markov Decision Processes (TVMDP) with partial observability and introduces Time-Varying Partially Observable Markov Decision Processes (TV-POMDP). We propose a twopronged approach to accurately estimate and plan within the TV-POMDP: 1) Memory Prioritized State Estimation (MPSE), which leverages weighted memory to provide more accurate time-varying transition estimates; and 2) an MPSE-integrated planning strategy that optimizes long-term rewards while accounting for temporal constraint. We validate the proposed framework and algorithms using simulations and hardware, with robots exploring a partially observable, time-varying environments. Our results demonstrate superior performance over standard methods, highlighting the framework’s effectiveness in stochastic, uncertain, time-varying domains.

Optimal decision-making for trajectory tracking in partially observable, stochastic environments where the number of active localization updates—the process by which the agent obtains its true state information from the sensors—are limited, presents a significant challenge. Traditional methods often struggle to balance resource conservation, accurate state estimation and precise tracking, resulting in suboptimal performance. This problem is particularly pronounced in environments with large action spaces, where the need for frequent, accurate state data is paramount, yet the capacity for active localization updates is restricted by external limitations. This paper introduces ComTraQ-MPC, a novel framework that combines Deep Q-Networks (DQN) and Model Predictive Control (MPC) to optimize trajectory tracking with constrained active localization updates. The meta-trained DQN ensures adaptive active localization scheduling, while the MPC leverages available state information to improve tracking. The central contribution of this work is their reciprocal interaction: DQN’s update decisions inform MPC’s control strategy, and MPC’s outcomes refine DQN’s learning, creating a cohesive, adaptive system. Empirical evaluations in simulated and real-world settings demonstrate that ComTraQ-MPC significantly enhances operational efficiency and accuracy, providing a generalizable and approximately optimal solution for trajectory tracking in complex partially observable environments. [Code]1[Video]2

Motivated by an emerging framework of Autonomous Modular Vehicles, we consider the abstract problem of optimally routing two modules, i.e., vehicles that can attach to or detach from each other in motion on a graph. The modules’ objective is to reach a preset set of nodes while incurring minimum resource costs. We assume that the resource cost incurred by an agent formed by joining two modules is the same as that of a single module. Such a cost formulation simplistically models the benefits of joining two modules, such as passenger redistribution between the modules, less traffic congestion, and higher fuel efficiency. To find an optimal plan, we propose a heuristic algorithm that uses the notion of graph centrality to determine when and where to join the modules. Additionally, we use the nearest neighbor approach to estimate the cost routing for joined or separated modules. Based on this estimated cost, the algorithm determines the subsequent nodes for both modules. The proposed algorithm is polynomial time: the worst-case number of calculations scale as the eighth power of the number of the total nodes in the graph. To validate its benefits, we simulate the proposed algorithm on a large number of pseudo-random graphs, motivated by real transportation scenario where it performs better than the most relevant benchmark, an adapted nearest neighbor algorithm for two separate agents, more than 85 percent of the time.

Autonomously selecting the right sequence of locations to sample is critical during exploration missions in unknown environments, with constraints on the number of samples that can be collected, and a possibility of system failure. A key idea for decision-making in unknown environments is to exploit side information available to the agent, combined with the information gained from samples collected so far, to estimate the sampling values. In this paper, we pose the problem of sampling site selection as a problem of finding the optimal policy in a Markov decision process modeling the unknown sampling values and the outcomes associated with sampling attempts at different locations. Our solution exploits the fact that the partially unknown rewards of this Markov decision process are correlated to each other to devise a strategy that attempts to maximize the total sample value while also ensuring that the agent achieves its minimum mission requirement. We validate the utility of the proposed approach by evaluating the method against a baseline strategy that pursues collecting the samples that are estimated to be of the highest value. Our evaluations use a simulated sampling problem on Martian terrain and using OceanWATERS, a high-fidelity simulator of a future Europa lander mission.

This paper proposes a formal approach to online learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations about the environment made by an agent earlier in the system run and assuming knowledge of a bound on the maximal rate of change of system dynamics. Such an approach generalizes the estimation method commonly used in learning algorithms for unknown Markov decision processes with time-invariant transition probabilities, but is also able to quickly and correctly identify the system dynamics following a change. Based on the proposed method, we generalize the exploration bonuses used in learning for time-invariant Markov decision processes by introducing a notion of uncertainty in a learned time-varying model, and develop a control policy for time-varying Markov decision processes based on the exploitation and exploration trade-off. We demonstrate the proposed methods on four numerical examples: a patrolling task with a change in system dynamics, a two-state MDP with periodically changing outcomes of actions, a wind flow estimation task, and a multi-armed bandit problem with periodically changing probabilities of different rewards.

Consumption Markov Decision Processes (CMDPs) are probabilistic decision-making models of resource-constrained systems. In a CMDP, the controller possesses a certain amount of a critical resource, such as electric power. Each action of the controller can consume some amount of the resource. Resource replenishment is only possible in special reload states, in which the resource level can be reloaded up to the full capacity of the system. The task of the controller is to prevent resource exhaustion, i.e. ensure that the available amount of the resource stays non-negative, while ensuring an additional linear-time property. We study the complexity of strategy synthesis in consumption MDPs with almost-sure Büchi objectives. We show that the problem can be solved in polynomial time. We implement our algorithm and show that it can efficiently solve CMDPs modelling real-world scenarios.