FORTE: Task-Adaptive Force Capability Optimization for Mobile Manipulators

Xiao Wang; Heng Zhang; Gokhan Solak; Fei Zhao; Arash Ajoudani

cs.ROSep 18, 2026

FORTE: Task-Adaptive Force Capability Optimization for Mobile Manipulators

Authors: Xiao Wang, Heng Zhang, Gokhan Solak, Fei Zhao, Arash Ajoudani

Organizations: HRI2 Lab, Istituto Italiano di Tecnologia, Genoa, 16163, Italy · Ph.D. program of national interest in Robotics and Intelligent Machines (DRIM) and University of Genova, Genoa, 16126, Italy · School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an, 710049, China

Abstract

Effective physical interaction control in robotic manipulation requires not only kinematically feasible motion but also sufficient force-interaction capability. Existing redundancy resolution methods often ignore task-specific force demands or maximize the force capability indiscriminately, sacrificing dexterity when large force margins are unnecessary. We propose a task-oriented force capability optimization framework for redundant mobile manipulators. A Vision-Language Model (VLM) infers object physical properties from an RGB image and a task description, generating a desired task-force sequence that captures gravitational and inertial demands. We then define a task-oriented force capability metric as the signed distance between a task-force uncertainty ball and the dynamic residual force polytope (RFP), quantifying compatibility between task demands and the robot's remaining actuation capacity. This metric is incorporated, alongside manipulability, joint-limit avoidance, trajectory smoothness, and base-oscillation suppression, into a whole-body multi-objective trajectory-optimization problem. Experiments on a mobile manipulator performing lifting and single-point-holding tasks under varying payload conditions demonstrate that the proposed method provides sufficient force capability for heavy loads while preserving high manipulability for light loads. This yields a task-adaptive balance that fixed capability-maximizing baselines (RFP inscribed radius, RFP cone) and manipulability-only optimization fail to achieve. The core implementation is publicly available at https://github.com/yeying256/FORTE.

Figures & tables

Fig. 1 : Overview of the proposed task-oriented force-capability optimization framework. Task-inefficient configurations may cause insufficient force capability for heavy payloads or limited manipulability for light payloads. The proposed framework estimates the task-force alignment, evaluates its compatibility with the robot’s residual force capability, and optimizes the whole-body configuration to achieve task-sufficient force capability while preserving manipulability.

Fig. 2 : Illustration of the construction of the dynamic Residual Force Polytope (RFP). The nominal torque $\tau_{\mathrm{nom},k}$ required to execute the trajectory is first computed from the joint position, velocity, and acceleration using inverse dynamics. The residual torque margins define the remaining admissible torque set $\mathcal{T}_{r,k}$ in joint space. By substituting the force-to-torque mapping $\tau_{f}=J_{v}^{T}(q_{k})f$ into the residual torque constraints, the joint-space residual actuation capability is mapped into the task-space dynamic residual force polytope $\mathcal{P}_{r,k}$ .

Fig. 3 : Overview of the proposed task-oriented force capability optimization framework. The framework consists of three main modules: VLM-based desired force estimation, force capability evaluation, and whole-body trajectory optimization. Given a task description $\mathcal{D}$ , an RGB image $\mathcal{I}$ , and a desired end-effector trajectory $\mathcal{X}_{d}$ , the VLM estimates task-related physical parameters and generates the desired force sequence $\mathcal{F}^{c}$ . The desired force at each trajectory point is modeled as the center of a task force uncertainty ball, while the Dynamic Residual Force Polytope (Dynamic RFP) characterizes the remaining force generation capability under the current robot configuration. The minimum signed distance between the task force uncertainty ball and the Dynamic RFP is used to construct the force capability cost. Finally, the force capability cost is jointly optimized with manipulability, joint-limit avoidance, trajectory smoothness, and base oscillation suppression using a constrained nonlinear programming solver to obtain the optimal whole-body trajectory.

Fig. 4 : Overview of the proposed desired force estimation module. Given a prompt-based task description $\mathcal{D}$ and an RGB image $\mathcal{I}$ , the VLM estimates the mass $\hat{m}$ of the manipulated object. Meanwhile, the desired end-effector trajectory $\mathcal{X}_{d}$ is processed by finite differences to obtain the end-effector acceleration ${}^{w}\ddot{p}_{e,k}$ . The estimated mass and the trajectory-induced acceleration are then combined with gravity compensation to compute the desired task force ${}^{w}f_{k}^{c}=\hat{m}({}^{w}\ddot{p}_{e,k}-{}^{w}g)$ at each waypoint. The resulting desired force sequence $\mathcal{F}^{c}$ serves as the task requirement representation for the subsequent force capability evaluation and trajectory optimization.

Panel of Figure 5 — Fig. 5 : Geometric illustration of the proposed force capability metric based on the relative position between the task force uncertainty ball and the Dynamic Residual Force Polytope (Dynamic RFP). The red circle denotes the task force uncertainty ball $\mathcal{B}_{k}$ , whose center is the desired task force ${}^{w}f_{k}^{c}$ and whose radius is $r_{k}$ . The blue polygon represents the Dynamic RFP $\mathcal{P}_{r,k}$ , which characterizes the available residual force generation capability at the $k$ -th waypoint. (a) The task force ball is fully contained inside the Dynamic RFP, yielding a positive force capability margin $d_{k}>0$ . (b) The task force ball is tangent to the boundary of the Dynamic RFP, corresponding to the critical case $d_{k}=0$ . (c) The task force ball extends outside the Dynamic RFP, indicating an insufficient force capability margin with $d_{k}<0$ .


Method	mALDE $\downarrow$	mAPE $\downarrow$	$r^{2}_{\mathrm{ls}}$ $\uparrow$	mMnRE $\uparrow$	$q$ $\uparrow$
Image2Mass (single-view)	0.465	0.685	0.691	0.675	0.766
Image2Mass (multi-view)	0.437	0.637	0.701	0.693	0.786
Ours (single-view)	$\mathbf{0.333}$	$\mathbf{0.377}$	$\mathbf{0.839}$	$\mathbf{0.742}$	$\mathbf{0.917}$

Table 1: Mass estimation performance on the Household Test Set (56 items, 423 images). The Image2Mass results are taken from [ 15 ] .


Parameter	Position trajectory	Task force
Offset $\mathbf{c}$	$\mathbf{0}$	$[25,\ 15,\ -65]^{\mathsf{T}}\,\mathrm{N}$
Amplitude $\mathbf{a}$	$[0.10,\ 0.10,\ -0.10]^{\mathsf{T}}\,\mathrm{m}$	$[80,\ 60,\ 80]^{\mathsf{T}}\,\mathrm{N}$
Frequency $\mathbf{f}$	$[0,\ 0.20,\ 0.10]^{\mathsf{T}}\,\mathrm{Hz}$	$[1/6,\ 1/4,\ 1/12]^{\mathsf{T}}\,\mathrm{Hz}$
Phase $\boldsymbol{\phi}$	$[\pi/2,\ 0,\ \pi/2]^{\mathsf{T}}$	$[0.5,\ \pi/2,\ \pi/4]^{\mathsf{T}}$
Duration	$T=12~\mathrm{s}$

Table 2: Parameters of the continuous trajectory and task-force simulation.

Fig. 6 : Directional force capability and arm translational manipulability under continuously varying task-force demands. Solid and dashed curves represent the RFP directional capability and manipulability, respectively. The black curve denotes the magnitude of the desired task force, and the shaded region represents the force uncertainty.

Fig. 7 : Overview of the experimental setup for the lifting and single-point holding experiments, including the mobile manipulator, payload conditions, and compared methods. The end-effector follows the indicated Cartesian trajectory in the lifting experiment and maintains a fixed desired Cartesian pose in the single-point holding experiment.

Panel of Figure 10 — Fig. 8 : Performance comparison of different planning methods in the 2.7 L and 0.33 L beverage lifting task. The upper plot shows the directional dynamic residual force polytope capacity, defined as the force magnitude at the intersection between the ray along the desired force direction and the boundary of the dynamic residual force polytope. The lower plot shows the arm manipulability. All curves report the mean over three trials, the shaded regions denote the standard deviation, and the orange band represents the uncertainty range of the desired task force.

Panel of Figure 11 — Fig. 9 : Single-point comparison of force output capability and manipulability under different payload conditions. The left vertical axis represents the directional residual force polytope capacity and the desired force range, while the right vertical axis represents the manipulability.

Panel of Figure 12 — Fig. 10 : Comparison of real-world single-point optimization results obtained by different optimization methods under 0.33 L and 2.7 L payload conditions. All methods optimize the same end-effector pose, while producing different robot configurations due to their respective optimization objectives.

Panel of Figure 13 — Fig. 11 : Single-point comparison under different payload conditions. Each column corresponds to one optimization method, and each row corresponds to one beverage load.

Panel of Figure 14 — Fig. 12 : Single-point comparison of manipulability ellipsoids under different payload conditions. Each column corresponds to one optimization method, and each row corresponds to one beverage load.

Force-Controlled Robotic Manipulation

Force-controlled robotic manipulation studies how robots regulate contact forces and compliance to grasp, assemble, and work safely with objects and surfaces.

See all 122 papers

ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation
Mar 16, 2026Yang Li, Zhaxizhuoma, Hongru Jiang +11Contact-Rich Robotic Manipulation Force-Controlled Robotic Manipulation
Tongji University · Shanghai AI Laboratory · Lumos Robotics +6
FP2: Equipping Robotic Foundation Models with Force Control
Sep 29, 2026Hongjie Fang, Shirun Tang, Junjian Hu +8Robotic Control Contact-Rich Robotic Manipulation
FORTE Lab. · Noematrix. · SJTU. +7
Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation
Sep 21, 2026Fukang Liu, Yipu Chen, Jaehwi Jang +3Contact-Rich Robotic Manipulation Humanoid Robot Control
Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA

Mar 16, 2026J/K move · Enter open · S save

ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation

Yang Li, Zhaxizhuoma, Hongru Jiang, Junjie Xia+10

Tongji University · Shanghai AI Laboratory · Lumos Robotics+6

Contact-Rich Robotic Manipulation Force-Controlled Robotic Manipulation VLMs for Robotics

Open paper AskPDF arXiv

Embodied intelligence for contact-rich manipulation has predominantly relied on position control, while explicit awareness and regulation of interaction forces remain under-explored, limiting stability, precision, and robustness in real-world tasks. We propose ForceVLA2, an end-to-end vision-language-action framework that equips robots with hybrid force-position control and explicit force awareness. ForceVLA2 introduces force-based prompts into the VLM expert to construct force-aware task concepts across stages, and employs a Cross-Scale Mixture-of-Experts (MoE) in the action expert to adaptively fuse these concepts with real-time interaction forces for closed-loop hybrid force-position regulation. To support learning and evaluation, we construct ForceVLA2-Dataset, containing 1,000 trajectories over 5 contact-rich tasks, including wiping, pressing, and assembling, with multi-view images, task prompts, proprioceptive state, and force signals. Extensive experiments show that ForceVLA2 substantially improves success rates and reliability in contact-rich manipulation, outperforming pi0 and pi0.5 by 48.0% and 35.0%, respectively, across the 5 tasks, and mitigating common failure modes such as arm overload and unstable contact, thereby actively advancing force-aware interactive physical intelligence in VLAs. The project page is available at https://sites.google.com/view/force-vla2/home.

Abstract

Force-Controlled Robotic Manipulation

Explore similar work

ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation

FP2: Equipping Robotic Foundation Models with Force Control

Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation